NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

2020/01/01 by Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik +3 · 81 citations
Computer Science · Engineering · #3D Shape Modeling and Analysis #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques

paper · doi:10.1007/978-3-030-58452-8_24

crossref issued 2020/01/01 · crossref published 2020/01/01 · crossref published-print 2020/01/01 · openalex publication_date 2020/01/01 · crossref published-online 2020/11/03 · crossref created 2020/11/03 · crossref deposited 2024/11/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30 · crossref indexed 2026/07/30

Citations

• Multilayer feedforward networks are universal approximators
• ShapeNet: An Information-Rich 3D Model Repository
• Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer

Cited by

• Learning Neural Light Fields with Ray-Space Embedding Networks
• Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces
• RGB-D Local Implicit Function for Depth Completion of Transparent Objects
• Toward an Automated System for Nondestructive Estimation of Plant Biomass
• NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo
• Style and Pose Control for Image Synthesis of Humans from a Single Monocular View
• Neural Fields in Visual Computing and Beyond
• Neural Image Representations for Multi-Image Fusion and Layer Separation
• STaR: Self-supervised Tracking and Reconstruction of Rigid Objects in Motion with Neural Rendering
• NeRV: Neural Representations for Videos
• Deep Direct Volume Rendering: Learning Visual Feature Mappings From Exemplary Images
• DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
• DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering
• MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images
• NeuTex: Neural Texture Mapping for Volumetric Neural Rendering
• Neural Trajectory Fields for Dynamic Novel View Synthesis
• Implicit Transformer Network for Screen Content Image Continuous Super-Resolution
• Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies
• MirrorNeRF: One-shot Neural Portrait Radiance Field from Multi-mirror Catadioptric Imaging
• SyntheticFur dataset for neural rendering
• InstaMap: instant-NGP for cryo-EM density maps
• Volume Rendering of Neural Implicit Surfaces
• Learning to Stylize Novel Views
• DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Rendering
• MarioNette: Self-Supervised Sprite Learning
• Hybrid Neural Fusion for Full-frame Video Stabilization
• FC2T2: The Fast Continuous Convolutional Taylor Transform with Applications in Vision and Graphics
• Instant neural graphics primitives with a multiresolution hash encoding
• Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering
• ACORN: Adaptive Coordinate Networks for Neural Scene Representation
• Avatars for the masses: smartphone-based reconstruction of humans for virtual reality
• Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image
• Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On
• On the Bias Against Inductive Biases
• 3D Scattering Tomography by Deep Learning with Architecture Tailored to\n Cloud Fields
• Positional Encoding as Spatial Inductive Bias in GANs
• Focal Frequency Loss for Image Reconstruction and Synthesis
• Real-time neural radiance caching for path tracing
• X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation
• In-Place Scene Labelling and Understanding with Implicit Scene Representation
• Depth-supervised NeRF: Fewer Views and Faster Training for Free
• NeRFReN: Neural Radiance Fields with Reflections
• Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering
• Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objects
• Deblur-NeRF: Neural Radiance Fields from Blurry Images
• AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis
• Generative Models as Distributions of Functions
• TyXe: Pyro-based Bayesian neural nets for Pytorch
• TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis
• pixelNeRF: Neural Radiance Fields from One or Few Images
• Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
• An Upper Limit of Decaying Rate with Respect to Frequency in Deep Neural Network
• Zero-Shot Text-Guided Object Generation with Dream Fields
• Rethinking Positional Encoding
• DOVE: Learning Deformable 3D Objects by Watching Videos
• Reconstruction of People in Loose Clothing
• Unsupervised Discovery of Object Radiance Fields
• Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction
• The impact of normal mapping on the appearance of geometrically simplified archaeological 3D models
• NeuMIP: Multi-Resolution Neural Materials
• Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields
• DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
• Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks
• Learning 3D Dense Correspondence via Canonical Point Autoencoder
• On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
• Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representations
• On the Effectiveness of Weight-Encoded Neural Implicit 3D Shapes
• Appearance Editing with Free-viewpoint Neural Rendering
• iButter: Neural Interactive Bullet Time Generator for Human Free-viewpoint Rendering
• Improved Transformer for High-Resolution GANs
• Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
• NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras
• NeRF++: Analyzing and Improving Neural Radiance Fields
• Neural Radiance Flow for 4D View Synthesis and Video Processing
• Semantically supervised appearance decomposition for virtual staging from a single panorama
• 3D Gaussian Splatting for Real-Time Radiance Field Rendering
• Uniform Generalization Bounds for Overparameterized Neural Networks
• Learning Neural Representation of Camera Pose with Matrix Representation of Pose Shift via View Synthesis
• Shelf-Supervised Mesh Prediction in the Wild
• Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes
• Light field [wikipedia]