mlsanityData to 7 Oct 2026

RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs

arXiv 2112.00724 ↗First posted 1 Dec 2021cs.CV cs.AI cs.GRcited by 614

Not on the map. Why?

Cited by 69 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Neural Radiance Fields (NeRF) have emerged as a powerful representation for the task of novel view synthesis due to their simplicity and state-of-the-art performance. Though NeRF can produce photorealistic renderings of unseen viewpoints when many input views are available, its performance drops significantly when this number is reduced. We observe that the majority of artifacts in sparse input scenarios are caused by errors in the estimated scene geometry, and by divergent behavior at the start of training. We address this by regularizing the geometry and appearance of patches rendered from unobserved viewpoints, and annealing the ray sampling space during training. We additionally use a normalizing flow model to regularize the color of unobserved viewpoints. Our model outperforms not only other methods that optimize over a single scene, but in many cases also conditional models that are extensively pre-trained on large multi-view datasets.

Key facts. Cited by 614 papers in the map (data through 7 Oct 2026). Builds on 53 of its 65 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

53 of 65 references.

References · 53

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  9. 2016Density estimation using Real NVPcited by 2,029
  10. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  11. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  12. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
38 more
  1. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  2. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  3. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  4. 2020Neural Sparse Voxel Fieldscited by 959
  5. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  6. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  7. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  8. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  9. 2020Convolutional Occupancy Networkscited by 760
  10. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  11. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  12. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  13. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  14. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  15. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  16. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  17. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  18. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  19. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 610
  20. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  21. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  22. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  23. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  24. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
  25. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  26. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  27. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  28. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  29. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  30. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  31. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  32. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  33. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  34. 2021Neural Lumigraph Renderingcited by 105
  35. 2019Learning to Infer Implicit Surfaces without 3D Supervisioncited by 103
  36. 2021GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worldscited by 98
  37. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  38. 2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 80

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 60; 2023: 177; 2024: 183; 2025: 125; 2026: 69.

614 papers.

Sort:

By area:

  1. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  2. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  3. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  4. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  5. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  6. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  7. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 341
  8. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  9. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  10. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  11. 2022Novel View Synthesis with Diffusion Modelscited by 299
  12. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 278
38 more
  1. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 256
  2. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  3. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  4. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  5. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  6. 2023Text-To-4D Dynamic Scene Generationcited by 204
  7. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  8. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  9. 2024CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussianscited by 190
  10. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  11. 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 172
  12. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  13. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  14. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  15. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 160
  16. 2022Instant Volumetric Head Avatarscited by 157
  17. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  18. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priorscited by 156
  19. 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videoscited by 156
  20. 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
  21. 2022ARF: Artistic Radiance Fieldscited by 147
  22. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistencycited by 143
  23. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 137
  24. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 136
  25. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  26. 2023SparseGS: Sparse View Synthesis using 3D Gaussian Splattingcited by 134
  27. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  28. 2022Reconstructing Personalized Semantic Facial NeRF Models From Monocular Videocited by 128
  29. 2023DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Modelscited by 127
  30. 2022NeRF-Art: Text-Driven Neural Radiance Fields Stylizationcited by 126
  31. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 120
  32. 2022Streaming Radiance Fields for 3D Video Synthesiscited by 118
  33. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  34. 2023Animate124: Animating One Image to 4D Dynamic Scenecited by 113
  35. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  36. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  37. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priorscited by 106
  38. 2023Progressively Optimized Local Radiance Fields for Robust View Synthesiscited by 103

50 most cited of 614 All 614 (JSON)