municef1 / Awesome-Avatars

List of recent advances for human avatars, including generation, reconstruction, and editing, etc.

Awesome Avatars

List of recent advances for human avatars, including generation, reconstruction, and editing, etc.

If you find any missed paper, feel free to open an issue or PR.

Table of Contents

• Awesome Avatars
  • Avatar Generation
  • Per-subject Avatar Reconstruction
  • Generalizable Avatar Novel View Synthesis
  • Generalizable Avatar Mesh Reconstruction
  • Text-to-Avatar
  • Avatar Interaction
  • Motion Generation
  • SMPL Estimation
  • Dataset
  • Aknowledgement

Avatar Generation

• Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations (ECCV 2022)
  

• GENERATIVE NEURAL ARTICULATED RADIANCE FIELDS (NeurIPS 2022)
  

• AvatarGen: a 3D Generative Model for Animatable Human Avatars (arXiv 01/08/2022)
  

• EVA3D: Compositional 3D Human Generation from 2D Image Collections (ICLR 2023 Spotlight)
  

• AG3D: Learning to Generate 3D Avatars from 2D Image Collections (ICCV 2023)
  

• Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors. (ICCV 2023)
  

• 3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective. (arXiv 2022)
  

Per-subject Avatar Reconstruction

• Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2021)
  

• Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies (ICCV 2021)
  

• Neural Human Radiance Field from a Single Video (ECCV 2022)
  

• HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video (CVPR 2022)
  

• MonoHuman: Animatable Human Neural Field from Monocular Video (CVPR 2023)
  

• InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds (CVPR 2023)
  

• Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition (CVPR 2023)
  

• Relightable and Animatable Neural Avatar from Sparse-View Video (arXiv 17/08/2023)
  

• TeCH: Text-guided Reconstruction of Lifelike Clothed Humans (3DV 2024)
  

• Learning Neural Volumetric Representations of Dynamic Humans in Minutes (CVPR 2023)
  

• HUGS: Human Gaussian Splats (Arxiv 2023)
  

• GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians (Arxiv 2023)
  

• GART: Gaussian Articulated Template Models (Arxiv 2023)
  

• Human101: Training 100+FPS Human Gaussians in 100s from 1 View (Arxiv 2023)
  

Generalizable Avatar Novel View Synthesis

• Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering (NeurIPS 2021)
  

• MPS-NeRF: Generalizable 3D Human Rendering from Multiview Images (TPAMI 2022)
  

• GP-NeRF: Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering (ECCV 2022)
  

• HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs (CVPR 2022)
  

• MonoNHR: Monocular Neural Human Renderer (3DV 2022)
  

• Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors (TVCG 2023)
  

• GHuNeRF: Generalizable Human NeRF from a Monocular Video (arXiv 03/09/2023)
  

• Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling (ICLR 2023)

  

• ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs (ICCV 2023)

  

• SHERF: Generalizable Human NeRF from a Single Image (ICCV 2023)
  

• TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering (ICCV 2023)
  

• GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis (Arxiv)
  

Generalizable Avatar Mesh Reconstruction

• ICON : Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2022)
  

• ECON: Explicit Clothed humans Optimized via Normal integration (CVPR 2023 Highlight)
  

• Structured 3D Features for Reconstructing Relightable and Animatable Avatars (CVPR 2023)
  

• SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction (CVPR 2023)
  

• DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction (CVPR 2023)
  

• Complete 3D Human Reconstruction from a Single Incomplete Image (CVPR 2023)
  

• High-fidelity 3D Human Digitization from Single 2K Resolution Images (CVPR 2023 Highlight)
  

• D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field (ICCV 2023)
  

• Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction (NeurIPS 2023)
  

Text-to-Avatar

• ZeroAvatar: Zero-shot 3D Avatar Generation from a Single Image. (arXiv 25/5/2023)
  

• DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models (arXiv 06/04/2023)
  

• DreamHuman: Animatable 3D Avatars from Text (arXiv 15/06/2023)
  

• AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose (arXiv 07/08/2023)
  

• Dancing Avatar: Pose and Text-Guided Human Motion Videos Synthesis with Image Diffusion Model (arXiv 15/08/2023)
  

• DreamWaltz: Make a Scene with Complex 3D Animatable Avatars (arXiv 12/07/2023)
  

• AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control (ICCV 2023)
  

• AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars (SIGGRAPH 2022)
  

• AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation (arXiv 16/06/2023)
  

• AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion (ACMMM 2023)
  

• TADA! Text to Animatable Digital Avatars (arXiv 2023)
  

• Guide3D: Create 3D Avatars from Text and Image Guidance (arXiv 2023)
  

• HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation (arXiv 2023)
  

• Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (Arxiv)
  

• HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting (Arxiv)
  

• InstructHumans: Editing Animatable 3D Human Textures with Instructions (Arxiv 2024)
  

Avatar Interaction

• Hi4D: 4D Instance Segmentation of Close Human Interaction (CVPR 2023)
  

• NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions. (CVPR 2023)
  

• HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video (CVPR 2023)
  

Motion Generation

• MotionGPT: Human Motion as a Foreign Language (arxiv)
  

• Executing your Commands via Motion Diffusion in Latent Space (CVPR 2023)
  

• TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis (ICCV 2023)
  

• Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation (ICCV 2023)
  

SMPL Estimation

• Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop (ICCV 2019)
  

• End-to-end human pose and mesh reconstruction with transformers. (CVPR 2021)
  

• Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation (CVPR 2021)
  

• GLAMR: Global occlusion-aware human mesh recovery with dynamic cameras (CVPR 2022 Oral)
  

• D&d: Learning human dynamics from dynamic camera (ECCV 2022 Oral)
  

• CLIFF: Carrying location information in full frames into human pose and shape estimation (ECCV 2022 Oral)
  

• Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation (CVPR 2023)
  

• JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery (ICCV 2023)
  

• TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments (CVPR 2023)
  

Dataset

• Function4D: Real-time Human Volumetric Capture from Very Sparse RGBD Sensors (Thuman-2.0 Dataset) (CVPR 2021 Oral)
  

• HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling (ECCV 2022 Oral)
  

• CLOTH4D: A Dataset for Clothed Human Reconstruction (CVPR 2023)
  

• High-fidelity 3D Human Digitization from Single 2K Resolution Images (2K2K) (CVPR 2023)
  

Aknowledgement

• We thank the template from Awesome-Video-Diffusion.

• The main contributors of this project are from ReLER Lab, CCAI, Zhejiang University.