mlsanityData to 7 Oct 2026

FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

arXiv 2303.07418 ↗First posted 13 Mar 2023cs.CVcited by 310

Not on the map. Why?

Cited by 33 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Novel view synthesis with sparse inputs is a challenging problem for neural radiance fields (NeRF). Recent efforts alleviate this challenge by introducing external supervision, such as pre-trained models and extra depth signals, and by non-trivial patch-based rendering. In this paper, we present Frequency regularized NeRF (FreeNeRF), a surprisingly simple baseline that outperforms previous methods with minimal modifications to the plain NeRF. We analyze the key challenges in few-shot neural rendering and find that frequency plays an important role in NeRF's training. Based on the analysis, we propose two regularization terms. One is to regularize the frequency range of NeRF's inputs, while the other is to penalize the near-camera density fields. Both techniques are ``free lunches'' at no additional computational cost. We demonstrate that even with one line of code change, the original NeRF can achieve similar performance as other complicated methods in the few-shot setting. FreeNeRF achieves state-of-the-art performance across diverse datasets, including Blender, DTU, and LLFF. We hope this simple baseline will motivate a rethinking of the fundamental role of frequency in NeRF's training under the low-data regime and beyond.

Key facts. Cited by 310 papers in the map (data through 7 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 13 Mar 2023.

Builds on

33 of 38 references.

References · 33

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  6. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  7. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  8. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  9. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  10. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  11. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  12. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
21 more
  1. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  2. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  3. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  4. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  5. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  6. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  7. 2021Neural Fields in Visual Computing and Beyondcited by 539
  8. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  9. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  10. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  11. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  12. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  13. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  14. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  15. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
  16. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  17. 2019Neural Volumes: Learning Dynamic Renderable Volumes from Imagescited by 173
  18. 2020DeRF: Decomposed Radiance Fieldscited by 163
  19. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  20. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 120
  21. 2021SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimizationcited by 59

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 45; 2024: 127; 2025: 87; 2026: 51.

310 papers.

Sort:

By area:

  1. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  2. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
  3. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  4. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  5. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 278
  6. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  7. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  8. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  9. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  10. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 160
  11. 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videoscited by 156
  12. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 139
38 more
  1. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  2. 2024Recent Advances in 3D Gaussian Splattingcited by 130
  3. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 120
  4. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  5. 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 111
  6. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priorscited by 106
  7. 2024FreGS: 3D Gaussian Splatting with Progressive Frequency Regularizationcited by 103
  8. 2024EscherNet: A Generative Model for Scalable View Synthesiscited by 94
  9. 2023VR-NeRF: High-Fidelity Virtualized Walkable Spacescited by 86
  10. 2024Fully Explicit Dynamic Gaussian Splattingcited by 75
  11. 2024Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splattingcited by 73
  12. 2024InstantSplat: Sparse-view Gaussian Splatting in Secondscited by 67
  13. 2023LEAP: Liberate Sparse-view 3D Modeling from Camera Posescited by 65
  14. 2025DropGaussian: Structural Regularization for Sparse-view Gaussian Splattingcited by 65
  15. 2023SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Explorationcited by 62
  16. 2024GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splattingcited by 59
  17. 2023Explicit Correspondence Matching for Generalizable Neural Radiance Fieldscited by 46
  18. 2024PhysMotion: Physics-Grounded Dynamics From a Single Imagecited by 45
  19. 2023SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutionscited by 44
  20. 2024Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstructioncited by 43
  21. 2024Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesiscited by 41
  22. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videoscited by 41
  23. 2023Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstructioncited by 39
  24. 2024On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategycited by 39
  25. 2023Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesiscited by 37
  26. 2024SGD: Street View Synthesis with Gaussian Splatting and Diffusion Priorcited by 36
  27. 2025GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priorscited by 36
  28. 2025Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splattingcited by 35
  29. 2024Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learningcited by 34
  30. 2024Relaxing Accurate Initialization Constraint for 3D Gaussian Splattingcited by 33
  31. 2023SpecNeRF: Gaussian Directional Encoding for Specular Reflectionscited by 30
  32. 2024How Far Can We Compress Instant-NGP-Based NeRF?cited by 30
  33. 2025Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigationcited by 30
  34. 2025Decompositional Neural Scene Reconstruction with Generative Diffusion Priorcited by 30
  35. 2024MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Viewscited by 29
  36. 2025Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputscited by 29
  37. 2025DropoutGS: Dropping Out Gaussians for Better Sparse-view Renderingcited by 29
  38. 20244D Gaussian Splatting in the Wild with Uncertainty-Aware Regularizationcited by 28

50 most cited of 310 All 310 (JSON)