A curated list of papers and open-source resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months. If you have any additions or suggestions, feel free to contribute. Additional resources like blog posts, videos, etc. are also welcome.
- Seminal Paper introducing 3D Gaussian Splatting
- Dynamics and Deformation
- Diffusion
- Avatars
- SLAM
- Mesh Extraction and Physics
- Regularization and Optimization
- Editing
- Rendering
- Compression
- Language Embedding
- Misc
- Classic work
- Open Source Implementations
- Blog Posts
- Tutorial Videos
- Credits
Update Log:
December 13, 2023:
- 3 papers added: Gaussian-SLAM, CoGS, and ASH.
December 11, 2023:
- 2 papers added: Gaussian Splatting SLAM and Denoising Scores for 3D Generation.
- ScaffoldGS code released.
December 8, 2023:
- 2 papers added: EAGLES and MonoGaussianAvatar.
December 7, 2023:
- LucidDreamer code released.
- 9 papers added: GauHuman, HeadGaS, HiFi4G, Gaussian-Flow, Feature-3DGS, Gaussian-Avatar, FlashAvatar, Relightable, and Deblurring Gaussians.
December 5, 2023:
- 9 papers added: NeuSG, GaussianHead, GaussianAvatars, GPS-Gaussian, Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction, SplaTAM, MANUS, Segment Any, and Language embedded 3D Gaussians.
December 4, 2023:
- 8 papers added: Gaussian Grouping, MD Splatting, DynMF, Scaffold-GS, SparseGS, FSGS, Control4D, and SC-GS.
December 1, 2023:
- 4 papers added: Compact3D, GaussianShader, Periodic Vibration Gaussian and Gaussian Shell Maps for Efficient 3D Human Generation.
- Created Table of contents for each category and added line breaks.
November 30, 2023:
- Added Unreal game engine implementation.
- 5 papers added: LightGaussian, FisherRF, HUGS, HumanGaussian, CG3D, and Multi Scale 3DGS.
November 29, 2023:
- Added two papers: Point and Move and IR-GS.
November 28, 2023:
- Added five papers: GaussinEditor, Relightable Gaussians, GART, Mip-Splatting, HumanGaussian.
November 27, 2023:
- Added two papers: Gaussian Editing and Compact 3D Gaussians.
November 25, 2023:
- Animatable Gaussians project added (paper not yet released).
November 22, 2023:
- 3 new GS papers added: Animatable, Depth-Regularized, and Monocular/Multi-view 3DGS.
- Added some classic papers.
- Added another GS paper also called LucidDreamer.
November 21, 2023:
- 3 new GS papers added: GaussianDiffusion, LucidDreamer, PhysGaussian.
- 2 more GS papers added: SuGaR, PhysGaussian.
November 21, 2023:
- Added the paper GS-SLAM
November 17, 2023:
- Added PlayCanvas implementation to Game Engines section.
November 16, 2023:
- Deformable 3D Gaussians code released.
- Drivable 3D Gaussian Avatars paper added.
November 8, 2023:
- Some notes about the 3DGS implementation and unsive/rsal format discussion.
November 4, 2023:
- Added 2D gaussian splatting.
- Added very detailed (technical) blog post explaining 3D gaussian splatting.
October 28, 2023:
- Added Utilities Section.
- Added 3DGS Converter for editing 3DGS .ply files in Cloud Compare to Utilities.
- Added Kapture (for bundler to colmap model conversion) and Kapture image cropper script with conversion instructions to Utilities.
October 23, 2023:
- Added python WebGL viewer 2.
- Added Intro to gaussian splatting (and Unity viewer) video blog.
October 21, 2023:
- Added python OpenGL viewer.
- Added typescript WebGPU viewer.
October 20, 2023:
- Made abstracts readable (removed hyphenations).
- Added Windows tutorial.
- Other minor text fixes.
- Added Jupyter notebook viewer.
October 19, 2023:
- Added Github page link for Real-time Photorealistic Dynamic Scene Representation.
- Re-ordered headings.
- Added other unofficial implementations.
- Moved Nerfstudio gsplat and fast: C++/CUDA to Unofficial Implementations.
- Added Nerfstudio, Blender, WebRTC, iOS & Metal viewers.
October 17, 2023:
- GaussianDreamer code released.
- Added Real-time Photorealistic Dynamic Scene Representation.
October 16, 2023:
- Added Deformable 3D Gaussians paper.
- Dynamic 3D Gaussians code released. October 15, 2023: Initial list with first 6 papers.
Authors: Bernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George Drettakis
Abstract
Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (≥ 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows real-time rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.📄 Paper (Low Resolution) | 📄 Paper (High Resolution) | 🌐 Project Page | 💻 Code | 🎥 Short Presentation | 🎥 Explanation Video
Authors: Jonathon Luiten, Georgios Kopanas, Bastian Leibe, Deva Ramanan
Abstract
We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree- of-freedom (6-DOF) tracking of all dense scene elements. We follow an analysis-by-synthesis framework, inspired by recent work that models scenes as a collection of 3D Gaussians which are optimized to reconstruct input images via differentiable rendering. To model dynamic scenes, we al- low Gaussians to move and rotate over time while enforcing that they have persistent color, opacity, and size. By regularizing Gaussians’ motion and rotation with local-rigidity constraints, we show that our Dynamic 3D Gaussians correctly model the same area of physical space over time, including the rotation of that space. Dense 6-DOF tracking and dynamic reconstruction emerges naturally from persistent dynamic view synthesis, without requiring any correspondence or flow as input. We demonstrate a large number of downstream applications enabled by our representation, including first-person view synthesis, dynamic compositional scene synthesis, and 4D video editing.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Explanation Video
Authors: Ziyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao, Yuqing Zhang, Xiaogang Jin
Abstract
Implicit neural representation has opened up new avenues for dynamic scene reconstruction and rendering. Nonetheless, state-of-the-art methods of dynamic neural rendering rely heavily on these implicit representations, which frequently struggle with accurately capturing the intricate details of objects in the scene. Furthermore, implicit methods struggle to achieve real-time rendering in general dynamic scenes, limiting their use in a wide range of tasks. To address the issues, we propose a deformable 3D Gaussians Splatting method that reconstructs scenes using explicit 3D Gaussians and learns Gaussians in canonical space with a deformation field to model monocular dynamic scenes. We also introduced a smoothing training mechanism with no extra overhead to mitigate the impact of inaccurate poses in real datasets on the smoothness of time interpolation tasks. Through differential gaussian rasterization, the deformable 3D Gaussians not only achieve higher rendering quality but also real-time rendering speed. Experiments show that our method outperforms existing methods significantly in terms of both rendering quality and speed, making it well-suited for tasks such as novel-view synthesis, time synthesis, and real-time rendering.📄 Paper | 🌐 Project Page | 💻 Code
Authors: Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Tian Qi, Xinggang Wang
Abstract
Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to maintain. We introduce the 4D Gaussian Splatting (4D-GS) to achieve real-time dynamic scene rendering while also enjoying high training and storage efficiency. An efficient deformation field is constructed to model both Gaussian motions and shape deformations. Different adjacent Gaussians are connected via a HexPlane to produce more accurate position and shape deformations. Our 4D-GS method achieves real-time rendering under high resolutions, 70 FPS at a 800×800 resolution on an RTX 3090 GPU, while maintaining comparable or higher quality than previous state-of-the-art method.📄 Paper | 🌐 Project Page | 💻 Code
Authors: Zeyu Yang, Hongye Yang, Zijie Pan, Xiatian Zhu, Li Zhang
Abstract
Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics. Despite advancements in neural implicit models, limitations persist: (i) Inadequate Scene Structure: Existing methods struggle to reveal the spatial and temporal structure of dynamic scenes from directly learning the complex 6D plenoptic function. (ii) Scaling Deformation Modeling: Explicitly modeling scene element deformation becomes impractical for complex dynamics. To address these issues, we consider the spacetime as an entirety and propose to approximate the underlying spatio-temporal 4D volume of a dynamic scene by optimizing a collection of 4D primitives, with explicit geometry and appearance modeling. Learning to optimize the 4D primitives enables us to synthesize novel views at any desired time with our tailored rendering routine. Our model is conceptually simple, consisting of a 4D Gaussian parameterized by anisotropic ellipses that can rotate arbitrarily in space and time, as well as view-dependent and time-evolved appearance represented by the coefficient of 4D spherindrical harmonics. This approach offers simplicity, flexibility for variable-length video and end-to-end training, and efficient real-time rendering, making it suitable for capturing complex dynamic scene motions. Experiments across various benchmarks, including monocular and multi-view scenarios, demonstrate our 4DGS model's superior visual quality and efficiency.📄 Paper | 💻 Code (to be released)
Authors: Kai Katsumata, Duc Minh Vo, Hideki Nakayama
Abstract
In novel view synthesis of scenes from multiple input views, 3D Gaussian splatting emerges as a viable alternative to existing radiance field approaches, delivering great visual quality and real-time rendering. While successful in static scenes, the present advancement of 3D Gaussian representation, however, faces challenges in dynamic scenes in terms of memory consumption and the need for numerous observations per time step, due to the onus of storing 3D Gaussian parameters per time step. In this study, we present an efficient 3D Gaussian representation tailored for dynamic scenes in which we define positions and rotations as functions of time while leaving other time-invariant properties of the static 3D Gaussian unchanged. Notably, our representation reduces memory usage, which is consistent regardless of the input sequence length. Additionally, it mitigates the risk of overfitting observed frames by accounting for temporal changes. The optimization of our Gaussian representation based on image and flow reconstruction results in a powerful framework for dynamic scene view synthesis in both monocular and multi-view cases. We obtain the highest rendering speed of 118 frames per second (FPS) at a resolution of 1352×1014 with a single GPU, showing the practical usability and effectiveness of our proposed method in dynamic scene rendering scenarios6. DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting
Authors: Agelos Kratimenos, Jiahui Lei, Kostas Daniilidis
Abstract
Accurately and efficiently modeling dynamic scenes and motions is considered so challenging a task due to temporal dynamics and motion complexity. To address these challenges, we propose DynMF, a compact and efficient representation that decomposes a dynamic scene into a few neural trajectories. We argue that the per-point motions of a dynamic scene can be decomposed into a small set of explicit or learned trajectories. Our carefully designed neural framework consisting of a tiny set of learned basis queried only in time allows for rendering speed similar to 3D Gaussian Splatting, surpassing 120 FPS, while at the same time, requiring only double the storage compared to static scenes. Our neural representation adequately constrains the inherently underconstrained motion field of a dynamic scene leading to effective and fast optimization. This is done by biding each point to motion coefficients that enforce the per-point sharing of basis trajectories. By carefully applying a sparsity loss to the motion coefficients, we are able to disentangle the motions that comprise the scene, independently control them, and generate novel motion combinations that have never been seen before. We can reach state-of-the-art render quality within just 5 minutes of training and in less than half an hour, we can synthesize novel views of dynamic scenes with superior photorealistic quality. Our representation is interpretable, efficient, and expressive enough to offer real-time view synthesis of complex dynamic scene motions, in monocular and multi-view scenarios.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Ruizhi Shao, Jingxiang Sun, Cheng Peng, Zerong Zheng, Boyao Zhou, Hongwen Zhang, Yebin Liu
Abstract
We introduce Control4D, an innovative framework for editing dynamic 4D portraits using text instructions. Our method addresses the prevalent challenges in 4D editing, notably the inefficiencies of existing 4D representations and the inconsistent editing effect caused by diffusion-based editors. We first propose GaussianPlanes, a novel 4D representation that makes Gaussian Splatting more structured by applying plane-based decomposition in 3D space and time. This enhances both efficiency and robustness in 4D editing. Furthermore, we propose to leverage a 4D generator to learn a more continuous generation space from inconsistent edited images produced by the diffusion-based editor, which effectively improves the consistency and quality of 4D editing. Comprehensive evaluation demonstrates the superiority of Control4D, including significantly reduced training time, high-quality rendering, and spatial-temporal consistency in 4D portrait editing.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Yi-Hua Huang, Yang-Tian Sun, Ziyi Yang, Xiaoyang Lyu, Yan-Pei Cao, Xiaojuan Qi
Abstract
Novel view synthesis for dynamic scenes is still a challenging problem in computer vision and graphics. Recently, Gaussian splatting has emerged as a robust technique to represent static scenes and enable high-quality and real-time novel view synthesis. Building upon this technique, we propose a new representation that explicitly decomposes the motion and appearance of dynamic scenes into sparse control points and dense Gaussians, respectively. Our key idea is to use sparse control points, significantly fewer in number than the Gaussians, to learn compact 6 DoF transformation bases, which can be locally interpolated through learned interpolation weights to yield the motion field of 3D Gaussians. We employ a deformation MLP to predict time-varying 6 DoF transformations for each control point, which reduces learning complexities, enhances learning abilities, and facilitates obtaining temporal and spatial coherent motion patterns. Then, we jointly learn the 3D Gaussians, the canonical space locations of control points, and the deformation MLP to reconstruct the appearance, geometry, and dynamics of 3D scenes. During learning, the location and number of control points are adaptively adjusted to accommodate varying motion complexities in different regions, and an ARAP loss following the principle of as rigid as possible is developed to enforce spatial continuity and local rigidity of learned motions. Finally, thanks to the explicit sparse motion representation and its decomposition from appearance, our method can enable user-controlled motion editing while retaining high-fidelity appearances. Extensive experiments demonstrate that our approach outperforms existing approaches on novel view synthesis with a high rendering speed and enables novel appearance-preserved motion editing applications.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Devikalyan Das, Christopher Wewer, Raza Yunus, Eddy Ilg, Jan Eric Lenssen
Abstract
Reconstructing dynamic objects from monocular videos is a severely underconstrained and challenging problem, and recent work has approached it in various directions. However, owing to the ill-posed nature of this problem, there has been no solution that can provide consistent, highquality novel views from camera positions that are significantly different from the training views. In this work, we introduce Neural Parametric Gaussians (NPGs) to take on this challenge by imposing a two-stage approach: first, we fit a low-rank neural deformation model, which then is used as regularization for non-rigid reconstruction in the second stage. The first stage learns the object’s deformations such that it preserves consistency in novel views. The second stage obtains high reconstruction quality by optimizing 3D Gaussians that are driven by the coarse model. To this end, we introduce a local 3D Gaussian representation, where temporally shared Gaussians are anchored in and deformed by local oriented volumes. The resulting combined model can be rendered as radiance fields, resulting in high-quality photo-realistic reconstructions of the non-rigidly deforming objects, maintaining 3D consistency across novel views. We demonstrate that NPGs achieve superior results compared to previous works, especially in challenging scenarios with few multi-view cues.Authors: Youtian Lin, Zuozhuo Dai, Siyu Zhu, Yao Yao
Abstract
We introduce Gaussian-Flow, a novel point-based approach for fast dynamic scene reconstruction and real-time rendering from both multi-view and monocular videos. In contrast to the prevalent NeRF-based approaches hampered by slow training and rendering speeds, our approach harnesses recent advancements in point-based 3D Gaussian Splatting (3DGS). Specifically, a novel Dual-Domain Deformation Model (DDDM) is proposed to explicitly model attribute deformations of each Gaussian point, where the time-dependent residual of each attribute is captured by a polynomial fitting in the time domain, and a Fourier series fitting in the frequency domain. The proposed DDDM is capable of modeling complex scene deformations across long video footage, eliminating the need for training separate 3DGS for each frame or introducing an additional implicit neural field to model 3D dynamics. Moreover, the explicit deformation modeling for discretized Gaussian points ensures ultra-fast training and rendering of a 4D scene, which is comparable to the original 3DGS designed for static 3D reconstruction. Our proposed approach showcases a substantial efficiency improvement, achieving a 5× faster training speed compared to the per-frame 3DGS modeling. In addition, quantitative results demonstrate that the proposed Gaussian-Flow significantly outperforms previous leading methods in novel view rendering quality.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Heng Yu, Joel Julin, Zoltán Á. Milacski, Koichiro Niinuma, László A. Jeni
Abstract
Capturing and re-animating the 3D structure of articulated objects present significant barriers. On one hand, methods requiring extensively calibrated multi-view setups are prohibitively complex and resource-intensive, limiting their practical applicability. On the other hand, while single-camera Neural Radiance Fields (NeRFs) offer a more streamlined approach, they have excessive training and rendering costs. 3D Gaussian Splatting would be a suitable alternative but for two reasons. Firstly, existing methods for 3D dynamic Gaussians require synchronized multi-view cameras, and secondly, the lack of controllability in dynamic scenarios. We present CoGS, a method for Controllable Gaussian Splatting, that enables the direct manipulation of scene elements, offering real-time control of dynamic scenes without the prerequisite of pre-computing control signals. We evaluated CoGS using both synthetic and real-world datasets that include dynamic objects that differ in degree of difficulty. In our evaluations, CoGS consistently outperformed existing dynamic and controllable neural representations in terms of visual fidelity.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Zilong Chen, Feng Wang, Huaping Liu
Abstract
In this paper, we present Gaussian Splatting based text-to-3D generation (GSGEN), a novel approach for generating high-quality 3D objects. Previous methods suffer from inaccurate geometry and limited fidelity due to the absence of 3D prior and proper representation. We leverage 3D Gaussian Splatting, a recent state-of-the-art representation, to address existing shortcomings by exploiting the explicit nature that enables the incorporation of 3D prior. Specifically, our method adopts a pro- gressive optimization strategy, which includes a geometry optimization stage and an appearance refinement stage. In geometry optimization, a coarse representation is established under a 3D geometry prior along with the ordinary 2D SDS loss, ensuring a sensible and 3D-consistent rough shape. Subsequently, the obtained Gaussians undergo an iterative refinement to enrich details. In this stage, we increase the number of Gaussians by compactness-based densification to enhance continuity and improve fidelity. With these designs, our approach can generate 3D content with delicate details and more accurate geometry. Extensive evaluations demonstrate the effectiveness of our method, especially for capturing high-frequency components.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation | 🎥 Explanation Video
Authors: Jiaxiang Tang, Jiawei Ren, Hang Zhou, Ziwei Liu, Gang Zeng
Abstract
Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their practical usage. In this paper, we propose DreamGaussian, a novel 3D content generation framework that achieves both efficiency and quality simultaneously. Our key insight is to design a generative 3D Gaussian Splatting model with companioned mesh extraction and texture refinement in UV space. In contrast to the occupancy pruning used in Neural Radiance Fields, we demonstrate that the progressive densification of 3D Gaussians converges significantly faster for 3D generative tasks. To further enhance the texture quality and facilitate downstream applications, we introduce an efficient algorithm to convert 3D Gaussians into textured meshes and apply a fine-tuning stage to refine the details. Extensive experiments demonstrate the superior efficiency and competitive generation quality of our proposed approach. Notably, DreamGaussian produces high-quality textured meshes in just 2 minutes from a single-view image, achieving approximately 10 times acceleration compared to existing methods.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Explanation Video
Authors: Taoran Yi1, Jiemin Fang, Guanjun Wu1, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Tian Qi, Xinggang Wang
Abstract
In recent times, the generation of 3D assets from text prompts has shown impressive results. Both 2D and 3D diffusion models can generate decent 3D objects based on prompts. 3D diffusion models have good 3D consistency, but their quality and generalization are limited as trainable 3D data is expensive and hard to obtain. 2D diffusion models enjoy strong abilities of generalization and fine generation, but the 3D consistency is hard to guarantee. This paper attempts to bridge the power from the two types of diffusion models via the recent explicit and efficient 3D Gaussian splatting representation. A fast 3D generation framework, named as GaussianDreamer, is proposed, where the 3D diffusion model provides point cloud priors for initialization and the 2D diffusion model enriches the geometry and appearance. Operations of noisy point growing and color perturbation are introduced to enhance the initialized Gaussians. Our GaussianDreamer can generate a high-quality 3D instance within 25 minutes on one GPU, much faster than previous methods, while the generated instances can be directly rendered in real time.📄 Paper | 🌐 Project Page | 💻 Code
4. GaussianDiffusion: 3D Gaussian Splatting for Denoising Diffusion Probabilistic Models with Structured Noise
Xinhai Li, Huaibin Wang, Kuo-Kun Tseng
Abstract
Text-to-3D, known for its efficient generation methods and expansive creative potential, has garnered significant attention in the AIGC domain. However, the amalgamation of Nerf and 2D diffusion models frequently yields oversaturated images, posing severe limitations on downstream industrial applications due to the constraints of pixelwise rendering method. Gaussian splatting has recently superseded the traditional pointwise sampling technique prevalent in NeRF-based methodologies, revolutionizing various aspects of 3D reconstruction. This paper introduces a novel text to 3D content generation framework based on Gaussian splatting, enabling fine control over image saturation through individual Gaussian sphere transparencies, thereby producing more realistic images. The challenge of achieving multi-view consistency in 3D generation significantly impedes modeling complexity and accuracy. Taking inspiration from SJC, we explore employing multi-view noise distributions to perturb images generated by 3D Gaussian splatting, aiming to rectify inconsistencies in multi-view geometry. We ingeniously devise an efficient method to generate noise that produces Gaussian noise from diverse viewpoints, all originating from a shared noise source. Furthermore, vanilla 3D Gaussian-based generation tends to trap models in local minima, causing artifacts like floaters, burrs, or proliferative elements. To mitigate these issues, we propose the variational Gaussian splatting technique to enhance the quality and stability of 3D appearance. To our knowledge, our approach represents the first comprehensive utilization of Gaussian splatting across the entire spectrum of 3D content generation processes.Yixun Liang, Xin Yang, Jiantao Lin, Haodong Li, Xiaogang Xu, Yingcong Chen
Abstract
The recent advancements in text-to-3D generation mark a significant milestone in generative models, unlocking new possibilities for creating imaginative 3D assets across various real-world scenarios. While recent advancements in text-to-3D generation have shown promise, they often fall short in rendering detailed and high-quality 3D models. This problem is especially prevalent as many methods base themselves on Score Distillation Sampling (SDS). This paper identifies a notable deficiency in SDS, that it brings inconsistent and low-quality updating direction for the 3D model, causing the over-smoothing effect. To address this, we propose a novel approach called Interval Score Matching (ISM). ISM employs deterministic diffusing trajectories and utilizes interval-based score matching to counteract over-smoothing. Furthermore, we incorporate 3D Gaussian Splatting into our text-to-3D generation pipeline. Extensive experiments show that our model largely outperforms the state-of-the-art in quality and training efficiency.Jaeyoung Chung, Suyoung Lee, Hyeongjin Nam, Jaerin Lee, Kyoung Mu Lee
Abstract
With the widespread usage of VR devices and contents, demands for 3D scene generation techniques become more popular. Existing 3D scene generation models, however, limit the target scene to specific domain, primarily due to their training strategies using 3D scan dataset that is far from the real-world. To address such limitation, we propose LucidDreamer, a domain-free scene generation pipeline by fully leveraging the power of existing large-scale diffusion-based generative model. Our LucidDreamer has two alternate steps: Dreaming and Alignment. First, to generate multi-view consistent images from inputs, we set the point cloud as a geometrical guideline for each image generation. Specifically, we project a portion of point cloud to the desired view and provide the projection as a guidance for inpainting using the generative model. The inpainted images are lifted to 3D space with estimated depth maps, composing a new points. Second, to aggregate the new points into the 3D scene, we propose an aligning algorithm which harmoniously integrates the portions of newly generated 3D scenes. The finally obtained 3D scene serves as initial points for optimizing Gaussian splats. LucidDreamer produces Gaussian splats that are highly-detailed compared to the previous 3D scene generation methods, with no constraint on domain of the target scene.📄 Paper | 🌐 Project Page | 💻 Code
Xian Liu, Xiaohang Zhan, Jiaxiang Tang, Ying Shan, Gang Zeng, Dahua Lin, Xihui Liu, Ziwei Liu
Abstract
Realistic 3D human generation from text prompts is a desirable yet challenging task. Existing methods optimize 3D representations like mesh or neural fields via score distillation sampling (SDS), which suffers from inadequate fine details or excessive training time. In this paper, we propose an efficient yet effective framework, HumanGaussian, that generates high-quality 3D humans with fine-grained geometry and realistic appearance. Our key insight is that 3D Gaussian Splatting is an efficient renderer with periodic Gaussian shrinkage or growing, where such adaptive density control can be naturally guided by intrinsic human structures. Specifically, 1) we first propose a Structure-Aware SDS that simultaneously optimizes human appearance and geometry. The multi-modal score function from both RGB and depth space is leveraged to distill the Gaussian densification and pruning process. 2) Moreover, we devise an Annealed Negative Prompt Guidance by decomposing SDS into a noisier generative score and a cleaner classifier score, which well addresses the over-saturation issue. The floating artifacts are further eliminated based on Gaussian size in a prune-only phase to enhance generation smoothness. Extensive experiments demonstrate the superior efficiency and competitive quality of our framework, rendering vivid 3D humans under diverse scenarios.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
Alexander Vilesov, Pradyumna Chari, Achuta Kadambi
Abstract
With the onset of diffusion-based generative models and their ability to generate text-conditioned images, content generation has received a massive invigoration. Recently, these models have been shown to provide useful guidance for the generation of 3D graphics assets. However, existing work in text-conditioned 3D generation faces fundamental constraints: (i) inability to generate detailed, multi-object scenes, (ii) inability to textually control multi-object configurations, and (iii) physically realistic scene composition. In this work, we propose CG3D, a method for compositionally generating scalable 3D assets that resolves these constraints. We find that explicit Gaussian radiance fields, parameterized to allow for compositions of objects, possess the capability to enable semantically and physically consistent scenes. By utilizing a guidance framework built around this explicit representation, we show state of the art results, capable of even exceeding the guiding diffusion model in terms of object combinations and physics accuracy.📄 Paper | 🌐 Project Page | | 🎥 Short Presentation
9.Learn to Optimize Denoising Scores for 3D Generation - A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting
Alexander Vilesov, Pradyumna Chari, Achuta Kadambi
Abstract
We propose a unified framework aimed at enhancing the diffusion priors for 3D generation tasks. Despite the critical importance of these tasks, existing methodologies often struggle to generate high-caliber results. We begin by examining the inherent limitations in previous diffusion priors. We identify a divergence between the diffusion priors and the training procedures of diffusion models that substantially impairs the quality of 3D generation. To address this issue, we propose a novel, unified framework that iteratively optimizes both the 3D model and the diffusion prior. Leveraging the different learnable parameters of the diffusion prior, our approach offers multiple configurations, affording various trade-offs between performance and implementation complexity. Notably, our experimental results demonstrate that our method markedly surpasses existing techniques, establishing new state-of-the-art in the realm of text-to-3D generation. Furthermore, our approach exhibits impressive performance on both NeRF and the newly introduced 3D Gaussian Splatting backbones. Additionally, our framework yields insightful contributions to the understanding of recent score distillation methods, such as the VSD and DDS loss.📄 Paper | 🌐 Project Page | 💻 Code
Authors: Wojciech Zielonka, Timur Bagautdinov, Shunsuke Saito, Michael Zollhöfer, Justus Thies, Javier Romero
Abstract
We present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats. Current photorealistic drivable avatars require either accurate 3D registrations during training, dense input images during testing, or both. The ones based on neural radiance fields also tend to be prohibitively slow for telepresence applications. This work uses the recently presented 3D Gaussian Splatting (3DGS) technique to render realistic humans at real-time framerates, using dense calibrated multi-view videos as input. To deform those primitives, we depart from the commonly used point deformation method of linear blend skinning (LBS) and use a classic volumetric deformation method: cage deformations. Given their smaller size, we drive these deformations with joint angles and keypoints, which are more suitable for communication applications. Our experiments on nine subjects with varied body shapes, clothes, and motions obtain higher-quality results than state-of-the-art methods when using the same training and test data.📄 Paper | 🌐 Project Page | 🎥 Short Presentation
Authors: Rohit Jena, Ganesh Subramanian Iyer, Siddharth Choudhary, Brandon Smith, Pratik Chaudhari, James Gee
Abstract
We propose SplatArmor, a novel approach for recovering detailed and animatable human models by `armoring' a parameterized body model with 3D Gaussians. Our approach represents the human as a set of 3D Gaussians within a canonical space, whose articulation is defined by extending the skinning of the underlying SMPL geometry to arbitrary locations in the canonical space. To account for pose-dependent effects, we introduce a SE(3) field, which allows us to capture both the location and anisotropy of the Gaussians. Furthermore, we propose the use of a neural color field to provide color regularization and 3D supervision for the precise positioning of these Gaussians. We show that Gaussian splatting provides an interesting alternative to neural rendering based methods by leverging a rasterization primitive without facing any of the non-differentiability and optimization challenges typically faced in such approaches. The rasterization paradigms allows us to leverage forward skinning, and does not suffer from the ambiguities associated with inverse skinning and warping. We show compelling results on the ZJU MoCap and People Snapshot datasets, which underscore the effectiveness of our method for controllable human synthesis.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Keyang Ye, Tianjia Shao, Kun Zhou
Abstract
We present a novel animatable 3D Gaussian model for rendering high-fidelity free-view human motions in real time. Compared to existing NeRF-based methods, the model owns better capability in synthesizing high-frequency details without the jittering problem across video frames. The core of our model is a novel augmented 3D Gaussian representation, which attaches each Gaussian with a learnable code. The learnable code serves as a pose-dependent appearance embedding for refining the erroneous appearance caused by geometric transformation of Gaussians, based on which an appearance refinement model is learned to produce residual Gaussian properties to match the appearance in target pose. To force the Gaussians to learn the foreground human only without background interference, we further design a novel alpha loss to explicitly constrain the Gaussians within the human body. We also propose to jointly optimize the human joint parameters to improve the appearance accuracy. The animatable 3D Gaussian model can be learned with shallow MLPs, so new human motions can be synthesized in real time (66 fps on avarage). Experiments show that our model has superior performance over NeRF-based methods.4. Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling
Authors: Zhe Li, Zerong Zheng, Lizhen Wang, Yebin Liu
Abstract
Modeling animatable human avatars from RGB videos is a long-standing and challenging problem. Recent works usually adopt MLP-based neural radiance fields (NeRF) to represent 3D humans, but it remains difficult for pure MLPs to regress pose-dependent garment details. To this end, we introduce Animatable Gaussians, a new avatar representation that leverages powerful 2D CNNs and 3D Gaussian splatting to create high-fidelity avatars. To associate 3D Gaussians with the animatable avatar, we learn a parametric template from the input videos, and then parameterize the template on two front & back canonical Gaussian maps where each pixel represents a 3D Gaussian. The learned template is adaptive to the wearing garments for modeling looser clothes like dresses. Such template-guided 2D parameterization enables us to employ a powerful StyleGAN-based CNN to learn the pose-dependent Gaussian maps for modeling detailed dynamic appearances. Furthermore, we introduce a pose projection strategy for better generalization given novel poses. Overall, our method can create lifelike avatars with dynamic, realistic and generalized appearances. Experiments show that our method outperforms other state-of-the-art approaches.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Jiahui Lei, Yufu Wang, Georgios Pavlakos, Lingjie Liu, Kostas Daniilidis
Abstract
We introduce Gaussian Articulated Template Model GART, an explicit, efficient, and expressive representation for non-rigid articulated subject capturing and rendering from monocular videos. GART utilizes a mixture of moving 3D Gaussians to explicitly approximate a deformable subject's geometry and appearance. It takes advantage of a categorical template model prior (SMPL, SMAL, etc.) with learnable forward skinning while further generalizing to more complex non-rigid deformations with novel latent bones. GART can be reconstructed via differentiable rendering from monocular videos in seconds or minutes and rendered in novel poses faster than 150fps.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
Authors: Arthur Moreau, Jifei Song, Helisa Dhamo, Richard Shaw, Yiren Zhou, Eduardo Pérez-Pellitero
Abstract
This work addresses the problem of real-time rendering of photorealistic human body avatars learned from multi-view videos. While the classical approaches to model and render virtual humans generally use a textured mesh, recent research has developed neural body representations that achieve impressive visual quality. However, these models are difficult to render in real-time and their quality degrades when the character is animated with body poses different than the training observations. We propose the first animatable human model based on 3D Gaussian Splatting, that has recently emerged as a very efficient alternative to neural radiance fields. Our body is represented by a set of gaussian primitives in a canonical space which are deformed in a coarse to fine approach that combines forward skinning and local non-rigid refinement. We describe how to learn our Human Gaussian Splatting (\OURS) model in an end-to-end fashion from multi-view observations, and evaluate it against the state-of-the-art approaches for novel pose synthesis of clothed body. Our method presents a PSNR 1.5dbB better than the state-of-the-art on THuman4 dataset while being able to render at 20fps or more.Authors: Muhammed Kocabas, Jen-Hao Rick Chang, James Gabriel, Oncel Tuzel, Anurag Ranjan
Abstract
Recent advances in neural rendering have improved both training and rendering times by orders of magnitude. While these methods demonstrate state-of-the-art quality and speed, they are designed for photogrammetry of static scenes and do not generalize well to freely moving humans in the environment. In this work, we introduce Human Gaussian Splats (HUGS) that represents an animatable human together with the scene using 3D Gaussian Splatting (3DGS). Our method takes only a monocular video with a small number of (50-100) frames, and it automatically learns to disentangle the static scene and a fully animatable human avatar within 30 minutes. We utilize the SMPL body model to initialize the human Gaussians. To capture details that are not modeled by SMPL (e.g. cloth, hairs), we allow the 3D Gaussians to deviate from the human body model. Utilizing 3D Gaussians for animated humans brings new challenges, including the artifacts created when articulating the Gaussians. We propose to jointly optimize the linear blend skinning weights to coordinate the movements of individual Gaussians during animation. Our approach enables novel-pose synthesis of human and novel view synthesis of both the human and the scene. We achieve state-of-the-art rendering quality with a rendering speed of 60 FPS while being ~100x faster to train over previous work.Authors: Rameen Abdal, Wang Yifan, Zifan Shi, Yinghao Xu, Ryan Po, Zhengfei Kuang, Qifeng Chen, Dit-Yan Yeung, Gordon Wetzstein
Abstract
Efficient generation of 3D digital humans is important in several industries, including virtual reality, social media, and cinematic production. 3D generative adversarial networks (GANs) have demonstrated state-of-the-art (SOTA) quality and diversity for generated assets. Current 3D GAN architectures, however, typically rely on volume representations, which are slow to render, thereby hampering the GAN training and requiring multi-view-inconsistent 2D upsamplers. Here, we introduce Gaussian Shell Maps (GSMs) as a framework that connects SOTA generator network architectures with emerging 3D Gaussian rendering primitives using an articulable multi shell–based scaffold. In this setting, a CNN generates a 3D texture stack with features that are mapped to the shells. The latter represent inflated and deflated versions of a template surface of a digital human in a canonical body pose. Instead of rasterizing the shells directly, we sample 3D Gaussians on the shells whose attributes are encoded in the texture features. These Gaussians are efficiently and differentiably rendered. The ability to articulate the shells is important during GAN training and, at inference time, to deform a body into arbitrary userdefined poses. Our efficient rendering scheme bypasses the need for view-inconsistent upsamplers and achieves highquality multi-view consistent renderings at a native resolution of 512 × 512 pixels. We demonstrate that GSMs successfully generate 3D humans when trained on single-view datasets, including SHHQ and DeepFashion.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Jie Wang, Xianyan Li, Jiucheng Xie, Feng Xu, Hao Gao
Abstract
Previous head avatar methods have mostly relied on fixed explicit primitives (mesh, point) or implicit surfaces (Sign Distance Function) and volumetric neural radiance field, it challenging to strike a balance among high fidelity, training speed, and resource consumption. The recent popularity of hybrid field has brought novel representation, but is limited by relying on parameterization factors obtained through fixed mappings. We propose GaussianHead: an head avatar algorithm based on anisotropic 3D gaussian primitives. We leverage canonical gaussians to represent dynamic scenes. Using explicit "dynamic" tri-plane as an efficient container for parameterized head geometry, aligned well with factors in the underlying geometry and tri-plane, we obtain aligned canonical factors for the canonical gaussians. With a tiny MLP, factors are decoded into opacity and spherical harmonic coefficients of 3D gaussian primitives. Finally, we use efficient differentiable gaussian rasterizer for rendering. Our approach benefits significantly from our novel representation based on 3D gaussians, and the proper alignment transformation of underlying geometry structures and factors in tri-plane eliminates biases introduced by fixed mappings. Compared to state-of-the-art techniques, we achieve optimal visual results in tasks such as self-reconstruction, novel view synthesis, and cross-identity reenactment while maintaining high rendering efficiency (0.12s per frame). Even the pores around the nose are clearly visible in some cases.📄 Paper | 🌐 Project Page | 💻 Code
Authors: Shenhan Qian, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Simon Giebenhain, Matthias Nießner
Abstract
We introduce GaussianAvatars, a new method to create photorealistic head avatars that are fully controllable in terms of expression, pose, and viewpoint. The core idea is a dynamic 3D representation based on 3D Gaussian splats that are rigged to a parametric morphable face model. This combination facilitates photorealistic rendering while allowing for precise animation control via the underlying parametric model, e.g., through expression transfer from a driving sequence or by manually changing the morphable model parameters. We parameterize each splat by a local coordinate frame of a triangle and optimize for explicit displacement offset to obtain a more accurate geometric representation. During avatar reconstruction, we jointly optimize for the morphable model parameters and Gaussian splat parameters in an end-to-end fashion. We demonstrate the animation capabilities of our photorealistic avatar in several challenging scenarios. For instance, we show reenactments from a driving video, where our method outperforms existing works by a significant margin.📄 Paper | 🌐 Project Page | 🎥 Short Presentation
11.GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis
Authors: Shunyuan Zheng, Boyao Zhou, Ruizhi Shao, Boning Liu, Shengping Zhang, Liqiang Nie, Yebin Liu
Abstract
We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner. The proposed method enables 2K-resolution rendering under a sparse-view camera setting. Unlike the original Gaussian Splatting or neural implicit rendering methods that necessitate per-subject optimizations, we introduce Gaussian parameter maps defined on the source views and regress directly Gaussian Splatting properties for instant novel view synthesis without any fine-tuning or optimization. To this end, we train our Gaussian parameter regression module on a large amount of human scan data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. The proposed framework is fully differentiable and experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed.📄 Paper (not ready) | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
Authors: Shoukang Hu Ziwei Liu
Abstract
We present, GauHuman, a 3D human model with Gaussian Splatting for both fast training (1~2 minutes) and real-time rendering (up to 189 FPS), compared with existing NeRF-based implicit representation modelling frameworks demanding hours of training and seconds of rendering per frame. Specifically, GauHuman encodes Gaussian Splatting in the canonical space and transforms 3D Gaussians from canonical space to posed space with linear blend skinning (LBS), in which effective pose and LBS refinement modules are designed to learn fine details of 3D humans under negligible computational cost. Moreover, to enable fast optimization of GauHuman, we initialize and prune 3D Gaussians with 3D human prior, while splitting/cloning via KL divergence guidance, along with a novel merge operation for further speeding up. Extensive experiments on ZJU_Mocap and MonoCap datasets demonstrate that GauHuman achieves state-of-the-art performance quantitatively and qualitatively with fast training and real-time rendering speed. Notably, without sacrificing rendering quality, GauHuman can fast model the 3D human performer with ~13k 3D Gaussians.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
Authors: Helisa Dhamo, Yinyu Nie, Arthur Moreau, Jifei Song, Richard Shaw, Yiren Zhou, Eduardo Pérez-Pellitero
Abstract
3D head animation has seen major quality and runtime improvements over the last few years, particularly empowered by the advances in differentiable rendering and neural radiance fields. Real-time rendering is a highly desirable goal for real-world applications. We propose HeadGaS, the first model to use 3D Gaussian Splats (3DGS) for 3D head reconstruction and animation. In this paper we introduce a hybrid model that extends the explicit representation from 3DGS with a base of learnable latent features, which can be linearly blended with low-dimensional parameters from parametric head models to obtain expression-dependent final color and opacity values. We demonstrate that HeadGaS delivers state-of-the-art results in real-time inference frame rates, which surpasses baselines by up to ~2dB, while accelerating rendering speed by over x10.Authors: Yuheng Jiang, Zhehao Shen, Penghao Wang, Zhuo Su, Yu Hong, Yingliang Zhang, Jingyi Yu, Lan Xu
Abstract
We have recently seen tremendous progress in photo-real human modeling and rendering. Yet, efficiently rendering realistic human performance and integrating it into the rasterization pipeline remains challenging. In this paper, we present HiFi4G, an explicit and compact Gaussian-based approach for high-fidelity human performance rendering from dense footage. Our core intuition is to marry the 3D Gaussian representation with non-rigid tracking, achieving a compact and compression-friendly representation. We first propose a dual-graph mechanism to obtain motion priors, with a coarse deformation graph for effective initialization and a fine-grained Gaussian graph to enforce subsequent constraints. Then, we utilize a 4D Gaussian optimization scheme with adaptive spatial-temporal regularizers to effectively balance the non-rigid prior and Gaussian updating. We also present a companion compression scheme with residual compensation for immersive experiences on various platforms. It achieves a substantial compression rate of approximately 25 times, with less than 2MB of storage per frame. Extensive experiments demonstrate the effectiveness of our approach, which significantly outperforms existing approaches in terms of optimization speed, rendering quality, and storage overhead.📄 Paper | 🌐 Project Page | 🎥 Short Presentation
15. GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians
Authors: Liangxiao Hu, Hongwen Zhang, Yuxiang Zhang, Boyao Zhou, Boning Liu, Shengping Zhang, Liqiang Nie
Abstract
We present GaussianAvatar, an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video. We start by introducing animatable 3D Gaussians to explicitly represent humans in various poses and clothing styles. Such an explicit and animatable representation can fuse 3D appearances more efficiently and consistently from 2D observations. Our representation is further augmented with dynamic properties to support pose-dependent appearance modeling, where a dynamic appearance network along with an optimizable feature tensor is designed to learn the motion-to-appearance mapping. Moreover, by leveraging the differentiable motion condition, our method enables a joint optimization of motions and appearances during avatar modeling, which helps to tackle the long-standing issue of inaccurate motion estimation in monocular settings. The efficacy of GaussianAvatar is validated on both the public dataset and our collected dataset, demonstrating its superior performances in terms of appearance quality and rendering efficiency.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
Authors: Jun Xiang, Xuan Gao, Yudong Guo, Juyong Zhang
Abstract
We propose FlashAvatar, a novel and lightweight 3D animatable avatar representation that could reconstruct a digital avatar from a short monocular video sequence in minutes and render high-fidelity photo-realistic images at 300FPS on a consumer-grade GPU. To achieve this, we maintain a uniform 3D Gaussian field embedded in the surface of a parametric face model and learn extra spatial offset to model non-surface regions and subtle facial details. While full use of geometric priors can capture high-frequency facial details and preserve exaggerated expressions, proper initialization can help reduce the number of Gaussians, thus enabling super-fast rendering speed. Extensive experimental results demonstrate that FlashAvatar outperforms existing works regarding visual quality and personalized details and is almost an order of magnitude faster in rendering speed.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Shunsuke Saito, Gabriel Schwartz, Tomas Simon, Junxuan Li, Giljoo Nam
Abstract
The fidelity of relighting is bounded by both geometry and appearance representations. For geometry, both mesh and volumetric approaches have difficulty modeling intricate structures like 3D hair geometry. For appearance, existing relighting models are limited in fidelity and often too slow to render in real-time with high-resolution continuous environments. In this work, we present Relightable Gaussian Codec Avatars, a method to build high-fidelity relightable head avatars that can be animated to generate novel expressions. Our geometry model based on 3D Gaussians can capture 3D-consistent sub-millimeter details such as hair strands and pores on dynamic face sequences. To support diverse materials of human heads such as the eyes, skin, and hair in a unified manner, we present a novel relightable appearance model based on learnable radiance transfer. Together with global illumination-aware spherical harmonics for the diffuse components, we achieve real-time relighting with spatially all-frequency reflections using spherical Gaussians. This appearance model can be efficiently relit under both point light and continuous illumination. We further improve the fidelity of eye reflections and enable explicit gaze control by introducing relightable explicit eye models. Our method outperforms existing approaches without compromising real-time performance. We also demonstrate real-time relighting of avatars on a tethered consumer VR headset, showcasing the efficiency and fidelity of our avatars.Authors: Yufan Chen, Lizhen Wang, Qijing Li, Hongjiang Xiao, Shengping Zhang, Hongxun Yao, Yebin Liu
Abstract
The ability to animate photo-realistic head avatars reconstructed from monocular portrait video sequences represents a crucial step in bridging the gap between the virtual and real worlds. Recent advancements in head avatar techniques, including explicit 3D morphable meshes (3DMM), point clouds, and neural implicit representation have been exploited for this ongoing research. However, 3DMM-based methods are constrained by their fixed topologies, point-based approaches suffer from a heavy training burden due to the extensive quantity of points involved, and the last ones suffer from limitations in deformation flexibility and rendering efficiency. In response to these challenges, we propose MonoGaussianAvatar (Monocular Gaussian Point-based Head Avatar), a novel approach that harnesses 3D Gaussian point representation coupled with a Gaussian deformation field to learn explicit head avatars from monocular portrait videos. We define our head avatars with Gaussian points characterized by adaptable shapes, enabling flexible topology. These points exhibit movement with a Gaussian deformation field in alignment with the target pose and expression of a person, facilitating efficient deformation. Additionally, the Gaussian points have controllable shape, size, color, and opacity combined with Gaussian splatting, allowing for efficient training and rendering. Experiments demonstrate the superior performance of our method, which achieves state-of-the-art results among previous methods.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
Authors: Haokai Pang, Heming Zhu, Adam Kortylewski, Christian Theobalt, Marc Habermann
Abstract
Real-time rendering of photorealistic and controllable human avatars stands as a cornerstone in Computer Vision and Graphics. While recent advances in neural implicit rendering have unlocked unprecedented photorealism for digital avatars, real-time performance has mostly been demonstrated for static scenes only. To address this, we propose ASH, an animatable Gaussian splatting approach for photorealistic rendering of dynamic humans in real-time. We parameterize the clothed human as animatable 3D Gaussians, which can be efficiently splatted into image space to generate the final rendering. However, naively learning the Gaussian parameters in 3D space poses a severe challenge in terms of compute. Instead, we attach the Gaussians onto a deformable character model, and learn their parameters in 2D texture space, which allows leveraging efficient 2D convolutional architectures that easily scale with the required number of Gaussians. We benchmark ASH with competing methods on pose-controllable avatars, demonstrating that our method outperforms existing real-time methods by a large margin and shows comparable or even better results than offline methods.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
Authors: Chi Yan, Delin Qu, Dong Wang, Dan Xu, Zhigang Wang, Bin Zhao, Xuelong Li
Abstract
In this paper, we introduce GS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better balance between efficiency and accuracy. Compared to recent SLAM methods employing neural implicit representations, our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D re-rendering. Specifically, we propose an adaptive expansion strategy that adds new or deletes noisy 3D Gaussian in order to efficiently reconstruct new observed scene geometry and improve the mapping of previously observed areas. This strategy is essential to extend 3D Gaussian representation to reconstruct the whole scene rather than synthesize a static object in existing methods. Moreover, in the pose tracking process, an effective coarse-to-fine technique is designed to select reliable 3D Gaussian representations to optimize camera pose, resulting in runtime reduction and robust estimation. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets. The source code will be released upon acceptance.Authors: Nikhil Keetha, Jay Karhade, Krishna Murthy Jatavallabhula, Gengshan Yang, Sebastian Scherer, Deva Ramanan, Jonathon Luiten
Abstract
Dense simultaneous localization and mapping (SLAM) is pivotal for embodied scene understanding. Recent work has shown that 3D Gaussians enable high-quality reconstruction and real-time rendering of scenes using multiple posed cameras. In this light, we show for the first time that representing a scene by 3D Gaussians can enable dense SLAM using a single unposed monocular RGB-D camera. Our method, SplaTAM, addresses the limitations of prior radiance field-based representations, including fast rendering and optimization, the ability to determine if areas have been previously mapped, and structured map expansion by adding more Gaussians. We employ an online tracking and mapping pipeline while tailoring it to specifically use an underlying Gaussian representation and silhouette-guided optimization via differentiable rendering. Extensive experiments show that SplaTAM achieves up to 2× state-of-theart performance in camera pose estimation, map construction, and novel-view synthesis, demonstrating its superiority over existing approaches, while allowing real-time rendering of a high-resolution dense 3D map.📄 Paper | 🌐 Project Page | 💻 Code
Authors: Hidenobu Matsuki, Riku Murai, Paul H. J. Kelly, Andrew J. Davison
Abstract
We present the first application of 3D Gaussian Splatting to incremental 3D reconstruction using a single moving monocular or RGB-D camera. Our Simultaneous Localisation and Mapping (SLAM) method, which runs live at 3fps, utilises Gaussians as the only 3D representation, unifying the required representation for accurate, efficient tracking, mapping, and high-quality rendering. Several innovations are required to continuously reconstruct 3D scenes with high fidelity from a live camera. First, to move beyond the original 3DGS algorithm, which requires accurate poses from an offline Structure from Motion (SfM) system, we formulate camera tracking for 3DGS using direct optimisation against the 3D Gaussians, and show that this enables fast and robust tracking with a wide basin of convergence. Second, by utilising the explicit nature of the Gaussians, we introduce geometric verification and regularisation to handle the ambiguities occurring in incremental 3D dense reconstruction. Finally, we introduce a full SLAM system which not only achieves state-of-the-art results in novel view synthesis and trajectory estimation, but also reconstruction of tiny and even transparent objects.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
Authors: Vladimir Yugay, Yue Li, Theo Gevers, Martin R. Oswald
Abstract
We present the first neural RGBD SLAM method capable of photorealistically reconstructing real-world scenes. Despite modern SLAM methods achieving impressive results on synthetic datasets, they still struggle with real-world datasets. Our approach utilizes 3D Gaussians as a primary unit for our scene representation to overcome the limitations of the previous methods. We observe that classical 3D Gaussians are hard to use in a monocular setup: they can't encode accurate geometry and are hard to optimize with single-view sequential supervision. By extending classical 3D Gaussians to encode geometry, and designing a novel scene representation and the means to grow, and optimize it, we propose a SLAM system capable of reconstructing and rendering real-world datasets without compromising on speed and efficiency. We show that Gaussian-SLAM can reconstruct and photorealistically render real-world scenes. We evaluate our method on common synthetic and real-world datasets and compare it against other state-of-the-art SLAM methods. Finally, we demonstrate, that the final 3D scene representation that we obtain can be rendered in Real-time thanks to the efficient Gaussian Splatting rendering.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
Authors: Tianyi Xie, Zeshun Zong, Yuxin Qiu, Xuan Li, Yutao Feng, Yin Yang, Chenfanfu Jiang
Abstract
We introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis. Employing a custom Material Point Method (MPM), our approach enriches 3D Gaussian kernels with physically meaningful kinematic deformation and mechanical stress attributes, all evolved in line with continuum mechanics principles. A defining characteristic of our method is the seamless integration between physical simulation and visual rendering: both components utilize the same 3D Gaussian kernels as their discrete representations. This negates the necessity for triangle/tetrahedron meshing, marching cubes, "cage meshes," or any other geometry embedding, highlighting the principle of "what you see is what you simulate (WS2)." Our method demonstrates exceptional versatility across a wide variety of materials--including elastic entities, metals, non-Newtonian fluids, and granular materials--showcasing its strong capabilities in creating diverse visual content with novel viewpoints and movements.📄 Paper | 🌐 Project Page | 💻 Code (not released yet) | 🎥 Short Presentation
2. SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering
Authors: Antoine Guédon, Vincent Lepetit
Abstract
We propose a method to allow precise and extremely fast mesh extraction from 3D Gaussian Splatting. Gaussian Splatting has recently become very popular as it yields realistic rendering while being significantly faster to train than NeRFs. It is however challenging to extract a mesh from the millions of tiny 3D gaussians as these gaussians tend to be unorganized after optimization and no method has been proposed so far. Our first key contribution is a regularization term that encourages the gaussians to align well with the surface of the scene. We then introduce a method that exploits this alignment to sample points on the real surface of the scene and extract a mesh from the Gaussians using Poisson reconstruction, which is fast, scalable, and preserves details, in contrast to the Marching Cubes algorithm usually applied to extract meshes from Neural SDFs. Finally, we introduce an optional refinement strategy that binds gaussians to the surface of the mesh, and jointly optimizes these Gaussians and the mesh through Gaussian splatting rendering. This enables easy editing, sculpting, rigging, animating, compositing and relighting of the Gaussians using traditional softwares by manipulating the mesh instead of the gaussians themselves. Retrieving such an editable mesh for realistic rendering is done within minutes with our method, compared to hours with the state-of-the-art methods on neural SDFs, while providing a better rendering quality.📄 Paper | 🌐 Project Page | 💻 Code (not released yet)
Authors: Bardienus P. Duisterhof, Zhao Mandi, Yunchao Yao, Jia-Wei Liu, Mike Zheng Shou, Shuran Song, Jeffrey Ichnowski
Abstract
Accurate 3D tracking in highly deformable scenes with occlusions and shadows can facilitate new applications in robotics, augmented reality, and generative AI. However, tracking under these conditions is extremely challenging due to the ambiguity that arises with large deformations, shadows, and occlusions. We introduce MD-Splatting, an approach for simultaneous 3D tracking and novel view synthesis, using video captures of a dynamic scene from various camera poses. MD-Splatting builds on recent advances in Gaussian splatting, a method that learns the properties of a large number of Gaussians for state-of-the-art and fast novel view synthesis. MD-Splatting learns a deformation function to project a set of Gaussians with non-metric, thus canonical, properties into metric space. The deformation function uses a neural-voxel encoding and a multilayer perceptron (MLP) to infer Gaussian position, rotation, and a shadow scalar. We enforce physics-inspired regularization terms based on local rigidity, conservation of momentum, and isometry, which leads to trajectories with smaller trajectory errors. MD-Splatting achieves high-quality 3D tracking on highly deformable scenes with shadows and occlusions. Compared to state-of-the-art, we improve 3D tracking by an average of 23.9 %, while simultaneously achieving high-quality novel view synthesis. With sufficient texture such as in scene 6, MD-Splatting achieves a median tracking error of 3.39 mm on a cloth of 1 x 1 meters in size📄 Paper | 🌐 Project Page | 💻 Code (not released yet)
Authors: Hanlin Chen, Chen Li, Gim Hee Lee
Abstract
Existing neural implicit surface reconstruction methods have achieved impressive performance in multi-view 3D reconstruction by leveraging explicit geometry priors such as depth maps or point clouds as regularization. However, the reconstruction results still lack fine details because of the over-smoothed depth map or sparse point cloud. In this work, we propose a neural implicit surface reconstruction pipeline with guidance from 3D Gaussian Splatting to recover highly detailed surfaces. The advantage of 3D Gaussian Splatting is that it can generate dense point clouds with detailed structure. Nonetheless, a naive adoption of 3D Gaussian Splatting can fail since the generated points are the centers of 3D Gaussians that do not necessarily lie on the surface. We thus introduce a scale regularizer to pull the centers close to the surface by enforcing the 3D Gaussians to be extremely thin. Moreover, we propose to refine the point cloud from 3D Gaussians Splatting with the normal priors from the surface predicted by neural implicit models instead of using a fixed set of points as guidance. Consequently, the quality of surface reconstruction improves from the guidance of the more accurate 3D Gaussian splatting. By jointly optimizing the 3D Gaussian Splatting and the neural implicit model, our approach benefits from both representations and generates complete surfaces with intricate details. Experiments on Tanks and Temples verify the effectiveness of our proposed method.Authors: Jaeyoung Chung, Jeongtaek Oh, Kyoung Mu Lee
Abstract
In this paper, we present a method to optimize Gaussian splatting with a limited number of images while avoiding overfitting. Representing a 3D scene by combining numerous Gaussian splats has yielded outstanding visual quality. However, it tends to overfit the training views when only a small number of images are available. To address this issue, we introduce a dense depth map as a geometry guide to mitigate overfitting. We obtained the depth map using a pre-trained monocular depth estimation model and aligning the scale and offset using sparse COLMAP feature points. The adjusted depth aids in the color-based optimization of 3D Gaussian splatting, mitigating floating artifacts, and ensuring adherence to geometric constraints. We verify the proposed method on the NeRF-LLFF dataset with varying numbers of few images. Our approach demonstrates robust geometry compared to the original method that relies solely on images.Authors: Joo Chan Lee, Daniel Rho, Xiangyu Sun, Jong Hwan Ko, Eunbyung Park
Abstract
Neural Radiance Fields (NeRFs) have demonstrated remarkable potential in capturing complex 3D scenes with high fidelity. However, one persistent challenge that hinders the widespread adoption of NeRFs is the computational bottleneck due to the volumetric rendering. On the other hand, 3D Gaussian splatting (3DGS) has recently emerged as an alternative representation that leverages a 3D Gaussisan-based representation and adopts the rasterization pipeline to render the images rather than volumetric rendering, achieving very fast rendering speed and promising image quality. However, a significant drawback arises as 3DGS entails a substantial number of 3D Gaussians to maintain the high fidelity of the rendered images, which requires a large amount of memory and storage. To address this critical issue, we place a specific emphasis on two key objectives: reducing the number of Gaussian points without sacrificing performance and compressing the Gaussian attributes, such as view-dependent color and covariance. To this end, we propose a learnable mask strategy that significantly reduces the number of Gaussians while preserving high performance. In addition, we propose a compact but effective representation of view-dependent color by employing a grid-based neural field rather than relying on spherical harmonics. Finally, we learn codebooks to compactly represent the geometric attributes of Gaussian by vector quantization. In our extensive experiments, we consistently show over 10× reduced storage and enhanced rendering speed, while maintaining the quality of the scene representation, compared to 3DGS. Our work provides a comprehensive framework for 3D scene representation, achieving high performance, fast training, compactness, and real-time rendering.📄 Paper | 🌐 Project Page | 💻 Code
Authors: Sharath Girish, Kamal Gupta, Abhinav Shrivastava
Abstract
Recently, 3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Neural Radiance Fields (NeRFs). Through rapid, differentiable rasterization of 3D Gaussians, 3D-GS achieves real-time rendering and accelerated training. They, however, demand substantial memory resources for both training and storage, as they require millions of Gaussians in their point cloud representation for each scene. We present a technique utilizing quantized embeddings to significantly reduce memory storage requirements and a coarse-to-fine training strategy for a faster and more stable optimization of the Gaussian point clouds. Our approach results in scene representations with fewer Gaussians and quantized representations, leading to faster training times and rendering speeds for real-time rendering of high resolution scenes. We reduce memory by more than an order of magnitude all while maintaining the reconstruction quality. We validate the effectiveness of our approach on a variety of datasets and scenes preserving the visual quality while consuming 10-20x less memory and faster training/inference speed.📄 Paper | 🌐 Project Page | 💻 Code
Authors: Yiwen Chen, Zilong Chen, Chi Zhang, Feng Wang, Xiaofeng Yang, Yikai Wang, Zhongang Cai, Lei Yang, Huaping Liu, Guosheng Lin
Abstract
3D editing plays a crucial role in many areas such as gaming and virtual reality. Traditional 3D editing methods, which rely on representations like meshes and point clouds, often fall short in realistically depicting complex scenes. On the other hand, methods based on implicit 3D representations, like Neural Radiance Field (NeRF), render complex scenes effectively but suffer from slow processing speeds and limited control over specific scene areas. In response to these challenges, our paper presents GaussianEditor, an innovative and efficient 3D editing algorithm based on Gaussian Splatting (GS), a novel 3D representation technique. GaussianEditor enhances precision and control in editing through our proposed Gaussian Semantic Tracing, which traces the editing target throughout the training process. Additionally, we propose hierarchical Gaussian splatting (HGS) to achieve stabilized and fine results under stochastic generative guidance from 2D diffusion models. We also develop editing strategies for efficient object removal and integration, a challenging task for existing methods. Our comprehensive experiments demonstrate GaussianEditor's superior control, efficacy, and rapid performance, marking a significant advancement in 3D editing.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
Authors: Jiemin Fang, Junjie Wang, Xiaopeng Zhang, Lingxi Xie, Qi Tian
Abstract
Recently, impressive results have been achieved in 3D scene editing with text instructions based on a 2D diffusion model. However, current diffusion models primarily generate images by predicting noise in the latent space, and the editing is usually applied to the whole image, which makes it challenging to perform delicate, especially localized, editing for 3D scenes. Inspired by recent 3D Gaussian splatting, we propose a systematic framework, named GaussianEditor, to edit 3D scenes delicately via 3D Gaussians with text instructions. Benefiting from the explicit property of 3D Gaussians, we design a series of techniques to achieve delicate editing. Specifically, we first extract the region of interest (RoI) corresponding to the text instruction, aligning it to 3D Gaussians. The Gaussian RoI is further used to control the editing process. Our framework can achieve more delicate and precise editing of 3D scenes than previous methods while enjoying much faster training speed, i.e. within 20 minutes on a single V100 GPU, more than twice as fast as Instruct-NeRF2NeRF (45 minutes -- 2 hours)📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
Authors: Jiajun Huang, Hongchuan Yu
Abstract
We propose Point'n Move, a method that achieves interactive scene object manipulation with exposed region inpainting. Interactivity here further comes from intuitive object selection and real-time editing. To achieve this, we adopt Gaussian Splatting Radiance Field as the scene representation and fully leverage its explicit nature and speed advantage. Its explicit representation formulation allows us to devise a 2D prompt points to 3D mask dual-stage self-prompting segmentation algorithm, perform mask refinement and merging, minimize change as well as provide good initialization for scene inpainting and perform editing in real-time without per-editing training, all leads to superior quality and performance. We test our method by performing editing on both forward-facing and 360 scenes. We also compare our method against existing scene object removal methods, showing superior quality despite being more capable and having a speed advantage.Authors: Mingqiao Ye, Martin Danelljan, Fisher Yu, Lei Ke
Abstract
The recent Gaussian Splatting achieves high-quality and real-time novel-view synthesis of the 3D scenes. However, it is solely concentrated on the appearance and geometry modeling, while lacking in fine-grained object-level scene understanding. To address this issue, we propose Gaussian Grouping, which extends Gaussian Splatting to jointly reconstruct and segment anything in open-world 3D scenes. We augment each Gaussian with a compact Identity Encoding, allowing the Gaussians to be grouped according to their object instance or stuff membership in the 3D scene. Instead of resorting to expensive 3D labels, we supervise the Identity Encodings during the differentiable rendering by leveraging the 2D mask predictions by SAM, along with introduced 3D spatial consistency regularization. Comparing to the implicit NeRF representation, we show that the discrete and grouped 3D Gaussians can reconstruct, segment and edit anything in 3D with high visual quality, fine granularity and efficiency. Based on Gaussian Grouping, we further propose a local Gaussian Editing scheme, which shows efficacy in versatile scene editing applications, including 3D object removal, inpainting, colorization and scene recomposition.Authors: Jiazhong Cen, Jiemin Fang, Chen Yang, Lingxi Xie, Xiaopeng Zhang, Wei Shen, Qi Tian
Abstract
Interactive 3D segmentation in radiance fields is an appealing task since its importance in 3D scene understanding and manipulation. However, existing methods face challenges in either achieving fine-grained, multi-granularity segmentation or contending with substantial computational overhead, inhibiting real-time interaction. In this paper, we introduce Segment Any 3D GAussians (SAGA), a novel 3D interactive segmentation approach that seamlessly blends a 2D segmentation foundation model with 3D Gaussian Splatting (3DGS), a recent breakthrough of radiance fields. SAGA efficiently embeds multi-granularity 2D segmentation results generated by the segmentation foundation model into 3D Gaussian point features through well-designed contrastive training. Evaluation on existing benchmarks demonstrates that SAGA can achieve competitive performance with state-of-the-art methods. Moreover, SAGA achieves multi-granularity segmentation and accommodates various prompts, including points, scribbles, and 2D masks. Notably, SAGA can finish the 3D segmentation within milliseconds, achieving nearly 1000× acceleration1 compared to previous SOTA.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Shijie Zhou, Haoran Chang, Sicheng Jiang, Zhiwen Fan, Zehao Zhu, Dejia Xu, Pradyumna Chari, Suya You, Zhangyang Wang, Achuta Kadambi
Abstract
3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis. In recent times, some work has emerged that aims to extend the functionality of NeRF beyond view synthesis, for semantically aware tasks such as editing and segmentation using 3D feature field distillation from 2D foundation models. However, these methods have two major limitations: (a) they are limited by the rendering speed of NeRF pipelines, and (b) implicitly represented feature fields suffer from continuity artifacts reducing feature quality. Recently, 3D Gaussian Splatting has shown state-of-the-art performance on real-time radiance field rendering. In this work, we go one step further: in addition to radiance field rendering, we enable 3D Gaussian splatting on arbitrary-dimension semantic features via 2D foundation model distillation. This translation is not straightforward: naively incorporating feature fields in the 3DGS framework leads to warp-level divergence. We propose architectural and training changes to efficiently avert this problem. Our proposed method is general, and our experiments showcase novel view semantic segmentation, language-guided editing and segment anything through learning feature fields from state-of-the-art 2D foundation models such as SAM and CLIP-LSeg. Across experiments, our distillation method is able to provide comparable or better results, while being significantly faster to both train and render. Additionally, to the best of our knowledge, we are the first method to enable point and bounding-box prompting for radiance field manipulation, by leveraging the SAM model.📄 Paper | 🌐 Project Page | 💻 Code (not yet) | 🎥 Short Presentation
Authors: Zehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler, Andreas Geiger
Abstract
Recently, 3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results, reaching high fidelity and efficiency. However, strong artifacts can be observed when changing the sampling rate, e.g., by changing focal length or camera distance. We find that the source for this phenomenon can be attributed to the lack of 3D frequency constraints and the usage of a 2D dilation filter. To address this problem, we introduce a 3D smoothing filter which constrains the size of the 3D Gaussian primitives based on the maximal sampling frequency induced by the input views, eliminating high frequency artifacts when zooming in. Moreover, replacing 2D dilation with a 2D Mip filter, which simulates a 2D box filter, effectively mitigates aliasing and dilation issues. Our comprehensive evaluation, including scenarios such as training on single-scale images and testing on multiple scales, validates the effectiveness of our approach.📄 Paper | 🌐 Project Page | 💻 Code
2. Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing
Authors: Jian Gao, Chun Gu, Youtian Lin, Hao Zhu, Xun Cao, Li Zhang, Yao Yao
Abstract
We present a novel differentiable point-based rendering framework for material and lighting decomposition from multi-view images, enabling editing, ray-tracing, and real-time relighting of the 3D point cloud. Specifically, a 3D scene is represented as a set of relightable 3D Gaussian points, where each point is additionally associated with a normal direction, BRDF parameters, and incident lights from different directions. To achieve robust lighting estimation, we further divide incident lights of each point into global and local components, as well as view-dependent visibilities. The 3D scene is optimized through the 3D Gaussian Splatting technique while BRDF and lighting are decomposed by physically-based differentiable rendering. Moreover, we introduce an innovative point-based ray-tracing approach based on the bounding volume hierarchy for efficient visibility baking, enabling real-time rendering and relighting of 3D Gaussian points with accurate shadow effects. Extensive experiments demonstrate improved BRDF estimation and novel view rendering results compared to state-of-the-art material estimation approaches. Our framework showcases the potential to revolutionize the mesh-based graphics pipeline with a relightable, traceable, and editable rendering pipeline solely based on point cloud.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Zhihao Liang, Qi Zhang, Ying Feng, Ying Shan, Kui Jia
Abstract
We propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (GS) that leverages forward mapping volume rendering to achieve photorealistic novel view synthesis and relighting results. Unlike previous works that use implicit neural representations and volume rendering (e.g. NeRF), which suffer from low expressive power and high computational complexity, we extend GS, a top-performance representation for novel view synthesis, to estimate scene geometry, surface material, and environment illumination from multi-view images captured under unknown lighting conditions. There are two main problems when introducing GS to inverse rendering: 1) GS does not support producing plausible normal natively; 2) forward mapping (e.g. rasterization and splatting) cannot trace the occlusion like backward mapping (e.g. ray tracing). To address these challenges, our GS-IR proposes an efficient optimization scheme that incorporates a depth-derivation-based regularization for normal estimation and a baking-based occlusion to model indirect lighting. The flexible and expressive GS representation allows us to achieve fast and compact geometry reconstruction, photorealistic novel view synthesis, and effective physically-based rendering. We demonstrate the superiority of our method over baseline methods through qualitative and quantitative evaluations on various challenging scenes.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Zhiwen Yan, Weng Fei Low, Yu Chen, Gim Hee Lee
Abstract
3D Gaussians have recently emerged as a highly efficient representation for 3D reconstruction and rendering. Despite its high rendering quality and speed at high resolutions, they both deteriorate drastically when rendered at lower resolutions or from far away camera position. During low resolution or far away rendering, the pixel size of the image can fall below the Nyquist frequency compared to the screen size of each splatted 3D Gaussian and leads to aliasing effect. The rendering is also drastically slowed down by the sequential alpha blending of more splatted Gaussians per pixel. To address these issues, we propose a multi-scale 3D Gaussian splatting algorithm, which maintains Gaussians at different scales to represent the same scene. Higher-resolution images are rendered with more small Gaussians, and lower-resolution images are rendered with fewer larger Gaussians. With similar training time, our algorithm can achieve 13\%-66\% PSNR and 160\%-2400\% rendering speed improvement at 4×-128× scale rendering on Mip-NeRF360 dataset compared to the single scale 3D Gaussian splatting.Authors: Yingwenqi Jiang, Jiadong Tu, Yuan Liu, Xifeng Gao, Xiaoxiao Long, Wenping Wang, Yuexin Ma
Abstract
The advent of neural 3D Gaussians has recently brought about a revolution in the field of neural rendering, facilitating the generation of high-quality renderings at real-time speeds. However, the explicit and discrete representation encounters challenges when applied to scenes featuring reflective surfaces. In this paper, we present GaussianShader, a novel method that applies a simplified shading function on 3D Gaussians to enhance the neural rendering in scenes with reflective surfaces while preserving the training and rendering efficiency. The main challenge in applying the shading function lies in the accurate normal estimation on discrete 3D Gaussians. Specifically, we proposed a novel normal estimation framework based on the shortest axis directions of 3D Gaussians with a delicately designed loss to make the consistency between the normals and the geometries of Gaussian spheres. Experiments show that GaussianShader strikes a commendable balance between efficiency and visual quality. Our method surpasses Gaussian Splatting in PSNR on specular object datasets, exhibiting an improvement of 1.57dB. When compared to prior works handling reflective surfaces, such as Ref-NeRF, our optimization time is significantly accelerated (23h vs. 0.58h). Please click on our project website to see more results.📄 Paper | 🌐 Project Page | 💻 Code
Authors: Tao Lu, Mulin Yu, Linning Xu, Yuanbo Xiangli, Limin Wang, Dahua Lin, Bo Dai
Abstract
Neural rendering methods have significantly advanced photo-realistic 3D scene rendering in various academic and industrial applications. The recent 3D Gaussian Splatting method has achieved the state-of-the-art rendering quality and speed combining the benefits of both primitive-based representations and volumetric representations. However, it often leads to heavily redundant Gaussians that try to fit every training view, neglecting the underlying scene geometry. Consequently, the resulting model becomes less robust to significant view changes, texture-less area and lighting effects. We introduce Scaffold-GS, which uses anchor points to distribute local 3D Gaussians, and predicts their attributes on-the-fly based on viewing direction and distance within the view frustum. Anchor growing and pruning strategies are developed based on the importance of neural Gaussians to reliably improve the scene coverage. We show that our method effectively reduces redundant Gaussians while delivering high-quality rendering. We also demonstrates an enhanced capability to accommodate scenes with varying levels-of-detail and view-dependent observations, without sacrificing the rendering speed.📄 Paper | 🌐 Project Page | 💻 Code
Authors: Haolin Xiong, Sairisheek Muttukuru, Rishi Upadhyay, Pradyumna Chari, Achuta Kadambi
Abstract
The problem of novel view synthesis has grown significantly in popularity recently with the introduction of Neural Radiance Fields (NeRFs) and other implicit scene representation methods. A recent advance, 3D Gaussian Splatting (3DGS), leverages an explicit representation to achieve real-time rendering with high-quality results. However, 3DGS still requires an abundance of training views to generate a coherent scene representation. In few shot settings, similar to NeRF, 3DGS tends to overfit to training views, causing background collapse and excessive floaters, especially as the number of training views are reduced. We propose a method to enable training coherent 3DGS-based radiance fields of 360 scenes from sparse training views. We find that using naive depth priors is not sufficient and integrate depth priors with generative and explicit constraints to reduce background collapse, remove floaters, and enhance consistency from unseen viewpoints. Experiments show that our method outperforms base 3DGS by up to 30.5% and NeRF-based methods by up to 15.6% in LPIPS on the MipNeRF-360 dataset with substantially less training and inference cost.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Zehao Zhu, Zhiwen Fan, Yifan Jiang, Zhangyang Wang
Abstract
Novel view synthesis from limited observations remains an important and persistent task. However, high efficiency in existing NeRF-based few-shot view synthesis is often compromised to obtain an accurate 3D representation. To address this challenge, we propose a few-shot view synthesis framework based on 3D Gaussian Splatting that enables real-time and photo-realistic view synthesis with as few as three training views. The proposed method, dubbed FSGS, handles the extremely sparse initialized SfM points with a thoughtfully designed Gaussian Unpooling process. Our method iteratively distributes new Gaussians around the most representative locations, subsequently infilling local details in vacant areas. We also integrate a large-scale pre-trained monocular depth estimator within the Gaussians optimization process, leveraging online augmented views to guide the geometric optimization towards an optimal solution. Starting from sparse points observed from limited input viewpoints, our FSGS can accurately grow into unseen regions, comprehensively covering the scene and boosting the rendering quality of novel views. Overall, FSGS achieves state-of-the-art performance in both accuracy and rendering efficiency across diverse datasets, including LLFF, Mip-NeRF360, and Blender📄 Paper | 🌐 Project Page | 💻 Code
Authors: Byeonghyeon Lee, Howoong Lee1, Xiangyu Sun, Usman Ali, and Eunbyung Park
Abstract
Novel-view synthesis of scenes acquired with several images or videos has been revolutionized by Radiance Field techniques. However, their high visual quality was achieved only with neural networks, which are costly to train and do not provide real-time rendering. Recently, 3D Gaussians splatting-based approach has been proposed to model the 3D scene, and it achieves state-of-the-art visual quality as well as renders in real-time. However, this approach suffers from severe degradation in the rendering quality if the training images are blurry. Several previous studies have attempted to render clean and sharp images from blurry input images using neural fields. However, the majority of those works are designed only for volumetric rendering-based neural fields and are not applicable to rasterization-based approaches. To fill this gap, we propose a novel neural field-based deblurring framework for the recently proposed rasterization-based approaches, 3D Gaussians, and rasterization. Specifically, we employ a small Multi-Layer Perceptron (MLP), which manipulates the covariance of each 3D Gaussian to model the scene blurriness. While deblurring 3D Gaussian Splatting can still enjoy real-time rendering, it can reconstruct fine and sharp details from blurry images. A variety of experiments have been conducted on the benchmark, and the results have revealed the effectiveness of our approach for deblurring.📄 Paper (not yet) | 🌐 Project Page | 💻 Code
Authors: Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
Abstract
Recent advancements in real-time neural rendering using point-based techniques have paved the way for the widespread adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting come with a substantial storage overhead caused by growing the SfM points to millions, often demanding gigabyte-level disk space for a single unbounded scene, posing significant scalability challenges and hindering the splatting efficiency. To address this challenge, we introduce LightGaussian, a novel method designed to transform 3D Gaussians into a more efficient and compact format. Drawing inspiration from the concept of Network Pruning, LightGaussian identifies Gaussians that are insignificant in contributing to the scene reconstruction and adopts a pruning and recovery process, effectively reducing redundancy in Gaussian counts while preserving visual effects. Additionally, LightGaussian employs distillation and pseudo-view augmentation to distill spherical harmonics to a lower degree, allowing knowledge transfer to more compact representations while maintaining reflectance. Furthermore, we propose a hybrid scheme, VecTree Quantization, to quantize all attributes, resulting in lower bitwidth representations with minimal accuracy losses. In summary, LightGaussian achieves an averaged compression rate over 15x while boosting the FPS from 139 to 215, enabling an efficient representation of complex scenes on Mip-NeRF 360, Tank and Temple datasets.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
Authors: KL Navaneet, Kossar Pourahmadi Meibodi, Soroush Abbasi Koohpayegani, Hamed Pirsiavash
Abstract
3D Gaussian Splatting is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods. However, it comes with a drawback in the much larger storage demand compared to NeRF methods since it needs to store the parameters for several 3D Gaussians. We notice that many Gaussians may share similar parameters, so we introduce a simple vector quantization method based on \kmeans algorithm to quantize the Gaussian parameters. Then, we store the small codebook along with the index of the code for each Gaussian. Moreover, we compress the indices further by sorting them and using a method similar to run-length encoding. We do extensive experiments on standard benchmarks as well as a new benchmark which is an order of magnitude larger than the standard benchmarks. We show that our simple yet effective method can reduce the storage cost for the original 3D Gaussian Splatting method by a factor of almost 20× with a very small drop in the quality of rendered images.Authors: Jin-Chuan Shi, Miao Wang, Hao-Bin Duan, Shao-Hua Guan
Abstract
Open-vocabulary querying in 3D space is challenging but essential for scene understanding tasks such as object localization and segmentation. Language-embedded scene representations have made progress by incorporating language features into 3D spaces. However, their efficacy heavily depends on neural networks that are resource-intensive in training and rendering. Although recent 3D Gaussians offer efficient and high-quality novel view synthesis, directly embedding language features in them leads to prohibitive memory usage and decreased performance. In this work, we introduce Language Embedded 3D Gaussians, a novel scene representation for open-vocabulary query tasks. Instead of embedding high-dimensional raw semantic features on 3D Gaussians, we propose a dedicated quantization scheme that drastically alleviates the memory requirement, and a novel embedding procedure that achieves smoother yet high accuracy query, countering the multi-view feature inconsistencies and the high-frequency inductive bias in point-based representations. Our comprehensive experiments show that our representation achieves the best visual quality and language querying accuracy across current language-embedded representations, while maintaining real-time rendering frame rates on a single desktop GPU.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
1. FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information
Authors: Wen Jiang, Boshu Lei, Kostas Daniilidis
Abstract
This study addresses the challenging problem of active view selection and uncertainty quantification within the domain of Radiance Fields. Neural Radiance Fields (NeRF) have greatly advanced image rendering and reconstruction, but the limited availability of 2D images poses uncertainties stemming from occlusions, depth ambiguities, and imaging errors. Efficiently selecting informative views becomes crucial, and quantifying NeRF model uncertainty presents intricate challenges. Existing approaches either depend on model architecture or are based on assumptions regarding density distributions that are not generally applicable. By leveraging Fisher Information, we efficiently quantify observed information within Radiance Fields without ground truth data. This can be used for the next best view selection and pixel-wise uncertainty quantification. Our method overcomes existing limitations on model architecture and effectiveness, achieving state-of-the-art results in both view selection and uncertainty quantification, demonstrating its potential to advance the field of Radiance Fields. Our method with the 3D Gaussian Splatting backend could perform view selections at 70 fps.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Yurui Chen, Chun Gu, Junzhe Jiang, Xiatian Zhu, Li Zhang
Abstract
Modeling dynamic, large-scale urban scenes is challenging due to their highly intricate geometric structures and unconstrained dynamics in both space and time. Prior methods often employ high-level architectural priors, separating static and dynamic elements, resulting in suboptimal capture of their synergistic interactions. To address this challenge, we present a unified representation model, called Periodic Vibration Gaussian (PVG). PVG builds upon the efficient 3D Gaussian splatting technique, originally designed for static scene representation, by introducing periodic vibration-based temporal dynamics. This innovation enables PVG to elegantly and uniformly represent the characteristics of various objects and elements in dynamic urban scenes. To enhance temporally coherent representation learning with sparse training data, we introduce a novel flow-based temporal smoothing mechanism and a position-aware adaptive control strategy. Extensive experiments on Waymo Open Dataset and KITTI benchmarks demonstrate that PVG surpasses state-of-the-art alternatives in both reconstruction and novel view synthesis for both dynamic and static scenes. Notably, PVG achieves this without relying on manually labeled object bounding boxes or expensive optical flow estimation. Moreover, PVG exhibits 50/6000-fold acceleration in training/rendering over the best alternative.📄 Paper | 🌐 Project Page | 💻 Code (not yet)
Authors: Chandradeep Pokhariya, Ishaan N Shah, Angela Xing, Zekun Li, Kefan Chen, Avinash Sharma, Srinath Sridhar
Abstract
Understanding how we grasp objects with our hands has important applications in areas like robotics and mixed reality. However, this challenging problem requires accurate modeling of the contact between hands and objects. To capture grasps, existing methods use skeletons, meshes, or parametric models that can cause misalignments resulting in inaccurate contacts. We present MANUS, a method for Markerless Hand-Object Grasp Capture using Articulated 3D Gaussians. We build a novel articulated 3D Gaussians representation that extends 3D Gaussian splatting for high-fidelity representation of articulating hands. Since our representation uses Gaussian primitives, it enables us to efficiently and accurately estimate contacts between the hand and the object. For the most accurate results, our method requires tens of camera views that current datasets do not provide. We therefore build MANUS-Grasps, a new dataset that contains hand-object grasps viewed from 53 cameras across 30+ scenes, 3 subjects, and comprising over 7M frames. In addition to extensive qualitative results, we also show that our method outperforms others on a quantitative contact evaluation method that uses paint transfer from the object to the hand.Authors: James F. Blinn
Comment:: First paper rendering 3D gaussians.
Abstract
The mathematical description of three-dimensional surfaces usually falls into one of two classifications: parametric and implicit. An implicit surface is defined to be all points which satisfy some equation F (x, y, z) = 0. This form is ideally suited for image space shaded picture drawing; the pixel coordinates are substituted for x and y, and the equation is solved for z. Algorithms for drawing such objects have been developed primarily for fLrst- and second-order polynomial functions, a subcategory known as algebraic surfaces. This paper presents a new algorithm applicable to other functional forms, in particular to the summation of several Gaussian density distributions. The algorithm was created to model electron density maps of molecular structures, but it can be used for other artistically interesting shapes.Authors: Leonid Keselman and Martial Hebert
Comment:: First paper to do differentiable rendering optimization of 3D gaussians.
Abstract
Differentiable renderers provide a direct mathematical link between an object’s 3D representation and images of that object. In this work, we develop an approximate differentiable renderer for a compact, interpretable representation, which we call Fuzzy Metaballs. Our approximate renderer focuses on rendering shapes via depth maps and silhouettes. It sacrifices fidelity for utility, producing fast runtimes and high-quality gradient information that can be used to solve vision tasks. Compared to mesh-based differentiable renderers, our method has forward passes that are 5x faster and backwards passes that are 30x faster. The depth maps and silhouette images generated by our method are smooth and defined everywhere. In our evaluation of differentiable renderers for pose estimation, we show that our method is the only one comparable to classic techniques. In shape from silhouette, our method performs well using only gradient descent and a per-pixel loss, without any surrogate losses or regularization. These reconstructions work well even on natural video sequences with segmentation artifacts.📄 Paper | 🌐 Project Page | 💻 Code | 🎥 Short Presentation
Authors: Jan U. Müller, Michael Weinmann, Reinhard Klein
Comment: Builds 2D screen-space gaussians from underlying 3D representations.
Abstract
The mathematical description of three-dimensional surfaces usually falls into one of two classifica- tions: parametric and implicit. An implicit surface is defined to be all points which satisfy some equation F (x, y, z) = 0. This form is ideally suited for image space shaded picture drawing; the pixel coordinates are substituted for x and y, and the equation is solved for z. Algorithms for drawing such objects have been developed primarily for fLrst- and second-order polynomial functions, a subcategory known as algebraic surfaces. This paper presents a new algorithm applicable to other functional forms, in particular to the summation of several Gaussian density distributions. The algorithm was created to model electron density maps of molecular structures, but it can be used for other artistically interesting shapes.Authors: Petr Man
Comment: Splatting of anisotropic gaussians. Basically a non-differentiable implementation of 3DGS.
Abstract
This paper presents a method for generation and real-time rendering of static clouds. Perlin noise function generates three dimensional map of a cloud. We also present a twopass rendering algorithm that performs physically based approximation. In the first preprocessed phase it computes multiple forward scattering. In the second phase first order anisotropic scattering at runtime is evaluated. The generated map is stored as voxels and is unsuitable for the real-time rendering. We introduce a more suitable inner representation of cloud that approximates the original map and contains much less information. The cloud is then represented by a set of metaballs (spheres) with parameters such as center positions, radii and density values. The main contribution of this paper is to propose a method, that transforms the original cloud map to the inner representation. This method uses the Radial Basis Function (RBF) neural network.- Taichi 3D Gaussian Splatting
- Gaussian Splatting 3D
- 3D Gaussian Splatting
- fast: C++/CUDA
- nerfstudio: python/CUDA
- WebGL Viewer 1
- WebGL Viewer 2
- WebGPU Viewer 1
- WebGPU Viewer 2
- Three.js
- A-Frame
- Nerfstudio Unofficial
- Nerfstudio Viser
- Blender (Editor)
- WebRTC viewer
- iOS & Metal viewer
- jupyter notebook
- python OpenGL viewer
- PlayCanvas Viewer
- gsplat.js
- Kapture - a unified data format to facilitate visual localization and structure from motion e.g. for bundler to colmap model conversion
- Kapture image cropper script - undistorted image cropper script to remove black borders with included conversion instructions
- camorph - a toolbox for conversion between camera parameter conventions e.g. Reality Capture to colmap model
- 3DGS Converter - a tool for converting 3D Gaussian Splatting .ply files into a format suitable for Cloud Compare and vice-versa.
- SuperSplat - open source browser-based tool to clean up and reorient .ply files
- Gaussian Splatting is pretty cool
- Making Gaussian Splats smaller
- Making Gaussian Splats more smaller
- Introduction to 3D Gaussian Splatting
- Very good (technical) intro to 3D Gaussian Splatting
- Write up on some mathematical details of the 3DGS implementation
- Discussion about gs universal format
- Math explanation to understand 3DGS
- Compressing Gaussian Splats
- Getting Started with 3DGS for Windows
- How to view 3DGS Scenes in Unity
- Two-minute explanation of 3DGS
- Jupyter notebook tutorial
- Intro to gaussian splatting (and Unity plugin)
- Thanks to Leonid Keselman for informing me about the release of the paper "Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting".
- Thanks to Eric Haines for suggesting the jupyter notebook viewer, windows tutorial and for fixing text hyphenations and other issues.
- Thanks to Henry Pearce for maintaining contributions.