mlsanityData to 7 Oct 2026

NAN: Noise-Aware NeRFs for Burst-Denoising

arXiv 2204.04668 ↗First posted 10 Apr 2022cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

Burst denoising is now more relevant than ever, as computational photography helps overcome sensitivity issues inherent in mobile phones and small cameras. A major challenge in burst-denoising is in coping with pixel misalignment, which was so far handled with rather simplistic assumptions of simple motion, or the ability to align in pre-processing. Such assumptions are not realistic in the presence of large motion and high levels of noise. We show that Neural Radiance Fields (NeRFs), originally suggested for physics-based novel-view rendering, can serve as a powerful framework for burst denoising. NeRFs have an inherent capability of handling noise as they integrate information from multiple images, but they are limited in doing so, mainly since they build on pixel-wise operations which are suitable to ideal imaging conditions. Our approach, termed NAN, leverages inter-view and spatial information in NeRFs to better deal with noise. It achieves state-of-the-art results in burst denoising and is especially successful in coping with large movement and occlusions, under very high levels of noise. With the rapid advances in accelerating NeRFs, it could provide a powerful platform for denoising in challenging environments.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 10 Apr 2022.

Builds on

27 of 34 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  5. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  7. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  8. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  9. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  10. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  11. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  12. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
15 more
  1. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  2. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  3. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  4. 2021Advances in Neural Renderingcited by 365
  5. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  6. 2020State of the Art on Neural Renderingcited by 276
  7. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  8. 2021Self-Calibrating Neural Radiance Fieldscited by 204
  9. 2017Burst Denoising with Kernel Prediction Networkscited by 156
  10. 2015EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flowcited by 80
  11. 2019Handheld Mobile Photography in Very Low Lightcited by 56
  12. 2017Deep Burst Denoisingcited by 49
  13. 2019Basis Prediction Networks for Effective Burst Denoising with Large Kernelscited by 46
  14. 2021Deep Reparametrization of Multi-Frame Super-Resolution and Denoisingcited by 39
  15. 2018Iterative Residual CNNs for Burst Photography Applicationscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 14; 2024: 18; 2025: 9; 2026: 4.

48 papers.

Sort:

By area:

  1. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  2. 2023SeaThru-NeRF: Neural Radiance Fields in Scattering Mediacited by 75
  3. 2023SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutionscited by 44
  4. 2023ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Imagescited by 38
  5. 2023Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumptioncited by 35
  6. 2024HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splattingcited by 35
  7. 2024DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAMcited by 22
  8. 2024DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Videocited by 17
  9. 2025NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Resultscited by 14
  10. 2023Benchmarking Robustness in Neural Radiance Fieldscited by 13
  11. 2024Leveraging Thermal Modality to Enhance Reconstruction in Low-Light Conditionscited by 12
  12. 2023USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fieldscited by 11
36 more
  1. 2024Hyperspectral Neural Radiance Fieldscited by 11
  2. 2023DehazeNeRF: Multiple Image Haze Removal and 3D Shape Reconstruction using Neural Radiance Fieldscited by 10
  3. 2023Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fieldscited by 9
  4. 2022Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photographycited by 8
  5. 2023SVNR: Spatially-variant Noise Removal with Denoising Diffusioncited by 8
  6. 2024RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Renderingcited by 8
  7. 2026Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesiscited by 8
  8. 2024Colorizing Monochromatic Radiance Fieldscited by 7
  9. 2025CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Imagescited by 7
  10. 2025Plenodium: UnderWater 3D Scene Reconstruction with Plenoptic Medium Representationcited by 7
  11. 2022Neural Volume Super-Resolutioncited by 5
  12. 2023Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representationscited by 5
  13. 2025SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splattingcited by 5
  14. 2023MF-NeRF: Memory Efficient NeRF with Mixed-Feature Hash Tablecited by 4
  15. 2024RaFE: Generative Radiance Fields Restorationcited by 4
  16. 2024NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Datasetcited by 4
  17. 2024Sparse-DeRF: Deblurred Neural Radiance Fields from Sparse Viewcited by 4
  18. 2023WaterHE-NeRF: Water-ray Tracing Neural Radiance Fields for Underwater Scene Reconstructioncited by 3
  19. 2024Radiance Fields from Photonscited by 3
  20. 2024Quanta Video Restorationcited by 3
  21. 2025Plug-and-Play Image Restoration with Flow Matching: A Continuous Viewpointcited by 3
  22. 2026Dark3R: Learning Structure from Motion in the Darkcited by 2
  23. 2026Toward Robust and 3D-Aware RGB-NIR Imaging in the Darkcited by 2
  24. 2023ReBotNet: Fast Real-time Video Enhancementcited by 1
  25. 2024Deep 3D World Models for Multi-Image Super-Resolution Beyond Optical Flowcited by 1
  26. 2024Learning Novel View Synthesis from Heterogeneous Low-light Capturescited by 1
  27. 2024Light Field Compression Based on Implicit Neural Representationcited by 1
  28. 2024NeRF-Aug: Data Augmentation for Robotics with Neural Radiance Fieldscited by 1
  29. 2024Towards Degradation-Robust Reconstruction in Generalizable NeRFcited by 1
  30. 2025Dynamic View Synthesis from Small Camera Motion Videoscited by 1
  31. 2025DenoiseGS: Gaussian Reconstruction Model for Burst Denoisingcited by 1
  32. 2025SuperF: Neural Implicit Fields for Multi-Image Super-Resolutioncited by 1
  33. 2026CompSplat: Compression-aware 3D Gaussian Splatting for Real-world Videocited by 1
  34. 2023Survey on Controlable Image Synthesis with Deep Learningcited by 0
  35. 2024U2NeRF: Unsupervised Underwater Image Restoration and Neural Radiance Fieldscited by 0
  36. 2025PhotonSplat: 3D Scene Reconstruction and Colorization from SPAD Sensorscited by 0