Awesome Neural Radiance Fields

A curated list of awesome neural radiance fields papers, inspired by awesome-computer-vision.

How to submit a pull request?

Table of Contents

• Survey
• Papers
• Talks

Survey

• Neural Volume Rendering: NeRF And Beyond, Dellaert and Yen-Chen, Arxiv 2020 | blog | github | bibtex

Papers

• NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, Mildenhall et al., ECCV 2020 | github | bibtex

Faster Inference

• Neural Sparse Voxel Fields, Liu et al., NeurIPS 2020 | github | bibtex
• AutoInt: Automatic Integration for Fast Neural Volume Rendering, Lindell et al., CVPR 2021 | github | bibtex
• DeRF: Decomposed Radiance Fields, Rebain et al. Arxiv 2020 | bibtex
• DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks, Neff et al., CGF 2021 | bibtex
• FastNeRF: High-Fidelity Neural Rendering at 200FPS, Garbin et al., Arxiv 2021 | bibtex
• KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs , Reiser et al., Arxiv 2021 | github | bibtex
• PlenOctrees for Real-time Rendering of Neural Radiance Fields, Yu et al., Arxiv 2021 | github | bibtex
• Mixture of Volumetric Primitives for Efficient Neural Rendering, Lombardi et al., SIGGRAPH 2021 | bibtex
• Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering, Sitzmann et al., Arxiv 2021 | bibtex

Faster Training

• Depth-supervised NeRF: Fewer Views and Faster Training for Free, Deng et al., Arxiv 2021 | github | bibtex
• Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction, Sun et al., Arxiv 2021 | github | bibtex

Unconstrained Images

• NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections, Martin-Brualla et al., CVPR 2021 | bibtex

Deformable

• Deformable Neural Radiance Fields, Park et al., Arxiv 2020 | github | bibtex
• D-NeRF: Neural Radiance Fields for Dynamic Scenes, Pumarola et al., CVPR 2021 | bibtex
• Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction, Gafni et al., CVPR 2021 | bibtex
• Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video, Tretschk et al., Arxiv 2020 | github | bibtex
• PVA: Pixel-aligned Volumetric Avatars, Raj et al., CVPR 2021 | bibtex
• Neural Articulated Radiance Field, Noguchi et al., Arxiv 2021 | bibtex
• Animatable Neural Radiance Fields for Human Body Modeling, Peng et al., Arxiv 2021 | bibtex
• A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields, Park et al., Arxiv 2021 | bibtex
• Animatable Neural Radiance Fields from Monocular RGB Videos, Chen et al., Arxiv 2021 | github | bibtex
• Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control, Liu et al., SIGGRAPH Asia 2021 | bibtex

Video

• Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes, Li et al., CVPR 2021 | github | bibtex
• Space-time Neural Irradiance Fields for Free-Viewpoint Video, Xian et al., CVPR 2021 | bibtex
• Neural Radiance Flow for 4D View Synthesis and Video Processing, Du et al., Arxiv 2020 | bibtex
• Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans, Peng et al., CVPR 2021 | bibtex
• Neural 3D Video Synthesis, Li et al., Arxiv 2021 | bibtex
• Dynamic View Synthesis from Dynamic Monocular Video, Gao et al., ICCV 2021 | bibtex

Generalization

• GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis, Schwarz et al., NeurIPS 2020 | github | bibtex
• GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering, Trevithick and Yang, Arxiv 2020 | github | bibtex
• pixelNeRF: Neural Radiance Fields from One or Few Images, Yu et al., CVPR 2021 | github | bibtex
• Learned Initializations for Optimizing Coordinate-Based Neural Representations, Tancik et al., CVPR 2021 | github | bibtex
• pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis, Chan et al., CVPR 2021 | bibtex
• Portrait Neural Radiance Fields from a Single Image, Gao et al., Arxiv 2020 | bibtex
• ShaRF: Shape-conditioned Radiance Fields from a Single View, Rematas et al., ICML 2021 | bibtex
• IBRNet: Learning Multi-View Image-Based Rendering, Wang et al., CVPR 2021 | github | bibtex
• CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields, Niemeyer & Geiger, Arxiv 2021 | bibtex
• NeRF-VAE: A Geometry Aware 3D Scene Generative Model, Kosiorek et al., Arxiv 2021 | bibtex
• Unconstrained Scene Generation with Locally Conditioned Radiance Fields, DeVries et al., Arxiv 2021 | bibtex
• MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo, Chen et al., Arxiv 2021 | github | bibtex
• Stereo Radiance Fields (SRF): Learning View Synthesis from Sparse Views of Novel Scenes, Chibane et al., CVPR 2021 | bibtex
• Neural Rays for Occlusion-aware Image-based Rendering, Liu et al., Arxiv 2021 | bibtex
• Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis, Matthew Tancik et al., Arxiv 2021 | bibtex
• MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis, Jiaxin Li et al., ICCV 2021 | github | bibtex
• TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis, Benjamin Attal et al., NeurIPS 2021 | bibtex
• CodeNeRF: Disentangled Neural Radiance Fields for Object Categories, Jang et al., ICCV 2021 | bibtex
• StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis, Gu et al., Arxiv 2021 | bibtex

Pose Estimation

• iNeRF: Inverting Neural Radiance Fields for Pose Estimation, Yen-Chen et al. IROS 2021 | bibtex
• A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering, Su et al. Arxiv 2021 | bibtex
• NeRF--: Neural Radiance Fields Without Known Camera Parameters, Wang et al., Arxiv 2021 | github | bibtex
• iMAP: Implicit Mapping and Positioning in Real-Time, Sucar et al., Arxiv 2021 | bibtex
• GNeRF: GAN-based Neural Radiance Field without Posed Camera, Meng et al., Arxiv 2021 | bibtex
• BARF: Bundle-Adjusting Neural Radiance Fields, Lin et al., ICCV 2021 | bibtex
• Self-Calibrating Neural Radiance Fields, Park et al., ICCV 2021 | github | bibtex

Lighting

• NeRD: Neural Reflectance Decomposition from Image Collections, Boss et al., Arxiv 2020 | github | bibtex
• NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis, Srinivasan et al. CVPR 2021 | bibtex
• NeX: Real-time View Synthesis with Neural Basis Expansion, Wizadwongsa et al. Arxiv 2021 | github | bibtex
• NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination, Zhang et al. Arxiv 2021 | github | bibtex

Compositionality

• NeRF++: Analyzing and Improving Neural Radiance Fields, Zhang et al., Arxiv 2020 | github | bibtex
• GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields, Niemeyer et al., CVPR 2021, bibtex
• Object-Centric Neural Scene Rendering, Guo et al., Arxiv 2020 | bibtex
• Learning Compositional Radiance Fields of Dynamic Human Heads, Wang et al., Arxiv 2020 | bibtex
• Neural Scene Graphs for Dynamic Scenes, Ost et al., CVPR 2021 | bibtex
• Unsupervised Discovery of Object Radiance Fields, Yu et al., Arxiv 2021 | bibtex
• Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering, Yang et al., ICCV 2021 | github | bibtex

Scene Labelling and Understanding

• In-Place Scene Labelling and Understanding with Implicit Scene Representation, Zhi et al., Arxiv 2021 | bibtex

Editing

• Editing Conditional Radiance Fields, Liu et al., Arxiv 2021 | github | bibtex
• Editable Free-viewpoint Video Using a Layered Neural Representation, Zhang et al., SIGGRAPH 2021 | github | bibtex

Object Category Modeling

• FiG-NeRF: Figure Ground Neural Radiance Fields for 3D Object Category Modelling, Xie et al., Arxiv 2021 | bibtex
• NeRF-Tex: Neural Reflectance Field Textures, Baatz et al., EGSR 2021 | bibtex

Multi-scale

• Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields, Barron et al., Arxiv 2021 | github | bibtex

Model Reconstruction

• UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction, Oechsle et al., ICCV 2021 | bibtex
• NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction, Wang et al., NeurIPS 2021 | github |bibtex

Depth Estimation

• NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo, Wei et al., ICCV 2021 | bibtex

Talks

• NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, Ben Mildenhall
• Understanding and Extending Neural Radiance Fields, Barron et al.
• Towards Photorealism (2nd half), Vladlen Koltun
• Neural Radiance Fields for View Synthesis, Matthew Tancik

Implementations

Tensorflow

• NeRF, Mildenhall et al., 2020 | bibtex

PyTorch

• NeRF-PyTorch, Yen-Chen Lin, 2020 | bibtex
• NeRF-PyTorch-Lighting, @kwea123, 2020
• NeRF-W, @kwea123, 2021
• NeRF-PyTorch3D, @facebookresearch, 2020

Jax

• JaxNeRF, Deng et al., 2020 | bibtex
• Mip-NeRF, @google, 2021 | bibtex

License

MIT