Collecting papers about new view synthesis
⭐🔥💪 I will update each day and add more details about every paper ☀️☀️☀️
-
Stereo Magnification: Learning View Synthesis using Multiplane Images [arxiv] | [code] | 2018
-
DeepView: View synthesis with learned gradient descent [pdf] | [code] | 2019
-
3D Ken Burns Effect from a Single Image [arxiv] | [code] | 2020
-
3D Photography using Context-aware Layered Depth Inpainting [arxiv] | [code] | 2020
-
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections [arxiv] | [code] | 2020
-
GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering [arxiv] | [code]
-
DeRF: Decomposed Radiance Fields [arxiv] | 2020
-
NeRF++: Analyzing and Improving Neural Radiance Fields [arxiv] | [code] | 2020
-
Generative View Synthesis: From Single-view Semantics to Novel-view Images [arxiv] | [code] | 2020
-
Single-view view synthesis with multiplane images [arxiv] | [code] | 2020
-
SynSin: End-to-end View Synthesis from a Single Image [arxiv] | [code] | 2020
-
MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images [arxiv] | [code] | 2020
-
Immersive light field video with a layered mesh representation [pdf] | [project] | 2020
-
NRMVS: Non-Rigid Multi-View Stereo [code] | 2019
-
Neural Volumes: Learning Dynamic Renderable Volumes from Images [arxiv] | [code] | 2020
-
Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3d human digitization [arxiv] | [code]
-
Neural3D: Light-weight Neural Portrait Scanning via Context-aware Correspondence Learning [pdf] | 2020
-
Monocular Real-Time Volumetric Performance Capture [pdf] | [code] | 2020
-
pixelNeRF : Neural Radiance Fields from One or Few Images [pdf] | [code] | 2020
-
Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera [arxiv] | 2020
-
Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes [arxiv] | [code] | 2020
-
Space-time Neural Irradiance Fields for Free-Viewpoint Video [arxiv] | [code] | 2020
-
NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis [project] | 2020
-
Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction [project] | 2020
- use 3DMM to get the facical expression
- encode the input image sqquences to get latent code
- like nerf's MLP, also use facial expressing and latent code as input for the Radiance Fields Network
-
NeRD: Neural Reflectance Decomposition from Image Collections [code] | 2020
-
Portrait Neural Radiance Fields from a Single Image [pdf] | [project] | 2020
-
Object-Centric Neural Scene Rendering [project] | 2020
-
Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image [project] | 2020
-
Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image [arxiv] | [video] | 2020
-
Neural Radiance Flow for 4D View Synthesis and Video Processing [project] | 2020
-
Learning Compositional Radiance Fields of Dynamic Human Heads [pdf] | [project] | 2020
-
Relightable 3D Head Portraits from a Smartphone Video [pdf] | 2020
-
Learning to Recover 3D Scene Shape from a Single Image [project] | 2020
-
Vid2Actor: Free-viewpoint Animatable Person Synthesis from Video in the Wild [project] | 2020
-
Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video [pdf] | 2020
-
ANR: Articulated Neural Rendering for Virtual Avatars [project] | 2020
-
Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans [pdf] | [project]
-
D-NeRF: Neural Radiance Fields for Dynamic Scenes [pdf]
-
Shape-conditioned Radiance Fields from a Single View [pdf] | [project]
-
NeRF--: Neural Radiance Fields Without Known Camera Parameters [pdf] | [project]
-
IBRNet: Learning Multi-View Image-Based Rendering [pdf] | [project]
-
DONeRF: Towards Real-Time Rendering of Neural Radiance Fields using Depth Oracle Networks [pdf] | [project]
-
NeX: Real-time View Synthesis with Neural Basis Expansion [pdf] | [project]
-
A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering [pdf] | [project]
-
FastNeRF: High-Fidelity Neural Rendering at 200FPS [pdf]
-
AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis [pdf]
-
AutoInt: Automatic Integration for Fast Neural Volume Rendering [pdf]
-
PlenOctrees for Real-time Rendering of Neural Radiance Fields [pdf] | [project]
-
KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs [pdf]
-
Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields [pdf]
-
Baking Neural Radiance Fields for Real-Time View Synthesis [pdf] | [project]
-
DDR-Net: Learning Multi-Stage Multi-View Stereo With Dynamic Depth Range [pdf] | [code]
-
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo [pdf] | [project]
-
GNeRF: GAN-based Neural Radiance Field without Posed Camera [pdf]
-
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video [project]
-
Putting NeRF on a Diet: Semantically Consistent Few-Shot View [pdf] | [project]
-
MirrorNeRF: One-shot Neural Portrait Radiance Field from Multi-mirror Catadioptric Imaging [pdf]
-
Pixel Codec Avatars [pdf]
-
Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes [pdf] | [code]
-
Geometry-Free View Synthesis: Transformers and no 3D Priors [pdf] | [code]
-
PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction [pdf] | [project]\
-
High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation [pdf]
-
UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction [pdf]
-
FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling [pdf] | [project]
-
BARF : Bundle-Adjusting Neural Radiance Fields [pdf] | [project]
-
NeMI: Unifying Neural Radiance Fields with Multiplane Images for Novel View Synthesis [pdf] | project
-
Neural Ray-Tracing: Learning Surfaces and Reflectance for Relighting and View Synthesis [pdf]
-
Animatable Neural Radiance Fields for Human Body Modeling [project]
-
Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors [pdf]
-
Editable Free-Viewpoint Video using a Layered Neural Representation [pdf]
-
LASR: Learning Articulated Shape Reconstruction from a Monocular Video [project]
-
Learning to Generate Novel Scene Compositions from Single Images and Videos [pdf]
-
POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture [project]
-
Deep Relightable Appearance Models for Animatable Faces [projcet]
-
Total Relighting:Learning to Relight Portraits for Background Replacement [project]
-
Dynamic View Synthesis from Dynamic Monocular Video [pdf]
-
Neural Trajectory Fields for Dynamic Novel View Synthesis [pdf]
-
NeLF: Practical Novel View Synthesis with Neural Light Field [pdf]
-
Recursive-NeRF: An Efficient and Dynamically Growing NeRF [pdf]
-
Convolutional Neural Opacity Radiance Fields [pdf]
-
Light Field Networks:Neural Scene Representations with Single-Evaluation Rendering [project]
-
NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination[project]
-
Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control[pdf] | [project]
-
DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Rendering [pdf] | [project]
-
Neural Implicit 3D Shapes from Single Images with Spatial Patterns [code]
-
NeRF in detail: Learning to sample for view synthesis [pdf]
-
View Generalization for Single Image Textured 3D Models [projet]
-
HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields [project]
-
FaDIV-Syn: Fast Depth-Independent View Synthesis [pdf]
-
Animatable Neural Radiance Fields from Monocular RGB Video [pdf]
-
Free-viewpoint Indoor Neural Relighting from Multi-view Stereo [pdf]
-
StylePeople A Generative Model of Fullbody Human Avatars [project]
-
Explicit Clothing Modeling for an Animatable Full-Body Avatar [pdf]
-
Depth-supervised NeRF: Fewer Views and Faster Training for Free [code]