mlsanityData to 14 Oct 2026

Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields

arXiv 2112.03907 ↗First posted 7 Dec 2021cs.CV cs.GRcited by 575

Not on the map. Why?

Cited by 39 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Neural Radiance Fields (NeRF) is a popular view synthesis technique that represents a scene as a continuous volumetric function, parameterized by multilayer perceptrons that provide the volume density and view-dependent emitted radiance at each location. While NeRF-based techniques excel at representing fine geometric structures with smoothly varying view-dependent appearance, they often fail to accurately capture and reproduce the appearance of glossy surfaces. We address this limitation by introducing Ref-NeRF, which replaces NeRF's parameterization of view-dependent outgoing radiance with a representation of reflected radiance and structures this function using a collection of spatially-varying scene properties. We show that together with a regularizer on normal vectors, our model significantly improves the realism and accuracy of specular reflections. Furthermore, we show that our model's internal representation of outgoing radiance is interpretable and useful for scene editing.

Key facts. Cited by 575 papers in the map (data through 14 Oct 2026). Builds on 21 of its 49 references that are in the map. First posted on arXiv 7 Dec 2021.

Builds on

21 of 49 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  4. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  7. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  8. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  9. 2020Neural Sparse Voxel Fieldscited by 959
  10. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  11. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  12. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
9 more
  1. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 467
  2. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 449
  3. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  4. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 335
  5. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  6. 2020Free View Synthesiscited by 231
  7. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 216
  8. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 205
  9. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 43; 2023: 197; 2024: 181; 2025: 97; 2026: 56.

575 papers.

Sort:

By area:

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  2. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  4. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  5. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
  6. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
  7. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
  8. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 476
  9. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  10. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 397
  11. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  12. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
38 more
  1. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 311
  2. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 311
  3. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 306
  4. 2022Novel View Synthesis with Diffusion Modelscited by 300
  5. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 297
  6. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  7. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 279
  8. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  9. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 221
  10. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  11. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  12. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 189
  13. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 184
  14. 2022Panoptic Lifting for 3D Scene Understanding with Neural Fieldscited by 174
  15. 2023HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Samplingcited by 174
  16. 2023TensoIR: Tensorial Inverse Renderingcited by 168
  17. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  18. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  19. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  20. 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videoscited by 160
  21. 2022Instant Volumetric Head Avatarscited by 159
  22. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 158
  23. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  24. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
  25. 2023HUGS: Human Gaussian Splatscited by 154
  26. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  27. 2023Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Renderingcited by 143
  28. 2023Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracingcited by 142
  29. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 138
  30. 2024Recent Advances in 3D Gaussian Splattingcited by 131
  31. 2023Consistent4D: Consistent 360deg Dynamic Object Generation from Monocular Videocited by 125
  32. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Modelscited by 125
  33. 2022Streaming Radiance Fields for 3D Video Synthesiscited by 119
  34. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  35. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 116
  36. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 115
  37. 2022Is Attention All That NeRF Needs?cited by 113
  38. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 112

50 most cited of 575 All 575 (JSON)