mlsanityData to 7 Oct 2026

BARF: Bundle-Adjusting Neural Radiance Fields

arXiv 2104.06405 ↗First posted 13 Apr 2021cs.CV cs.GR cs.LGcited by 641

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Neural Radiance Fields (NeRF) have recently gained a surge of interest within the computer vision community for its power to synthesize photorealistic novel views of real-world scenes. One limitation of NeRF, however, is its requirement of accurate camera poses to learn the scene representations. In this paper, we propose Bundle-Adjusting Neural Radiance Fields (BARF) for training NeRF from imperfect (or even unknown) camera poses -- the joint problem of learning neural 3D representations and registering camera frames. We establish a theoretical connection to classical image alignment and show that coarse-to-fine registration is also applicable to NeRF. Furthermore, we show that na"ively applying positional encoding in NeRF has a negative impact on registration with a synthesis-based objective. Experiments on synthetic and real-world data show that BARF can effectively optimize the neural scene representations and resolve large camera pose misalignment at the same time. This enables view synthesis and localization of video sequences from unknown camera poses, opening up new avenues for visual localization systems (e.g. SLAM) and potential applications for dense 3D mapping and reconstruction.

Key facts. Cited by 641 papers in the map (data through 7 Oct 2026). Builds on 40 of its 72 references that are in the map. First posted on arXiv 13 Apr 2021.

Builds on

40 of 72 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  5. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  6. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  7. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  8. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  9. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  10. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  11. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  12. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
28 more
  1. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  2. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  3. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  4. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  5. 2016Direct Sparse Odometrycited by 479
  6. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  7. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  8. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
  9. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  10. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  11. 2020State of the Art on Neural Renderingcited by 276
  12. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  13. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  14. 2020Free View Synthesiscited by 231
  15. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  16. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  17. 2020Stable View Synthesiscited by 165
  18. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  19. 2018LF-Net: Learning Local Features from Imagescited by 151
  20. 2019Neural Rerendering in the Wildcited by 121
  21. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  22. 2018Layer-structured 3D Scene Inference via View Synthesiscited by 82
  23. 2020Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Imagecited by 77
  24. 2020Portrait Neural Radiance Fields from a Single Imagecited by 61
  25. 2017Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Camerascited by 45
  26. 2019Photometric Mesh Optimization for Video-Aligned 3D Object Reconstructioncited by 28
  27. 2016Photometric Bundle Adjustment for Vision-Based SLAMcited by 25
  28. 2021Asynchronous Multi-View SLAMcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 102; 2023: 174; 2024: 203; 2025: 103; 2026: 34.

641 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  3. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  4. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  5. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  6. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  7. 2021Neural Fields in Visual Computing and Beyondcited by 539
  8. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  9. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 396
  10. 2021Advances in Neural Renderingcited by 365
  11. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 359
  12. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
38 more
  1. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  2. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  3. 2021Urban Radiance Fieldscited by 263
  4. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  5. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  6. 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
  7. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  8. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  9. 2021BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Renderingcited by 228
  10. 2023Visual Geometry Grounded Deep Structure From Motioncited by 225
  11. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  12. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
  13. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 204
  14. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  15. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  16. 2023Robust Dynamic Radiance Fieldscited by 193
  17. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  18. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  19. 2021Deblur-NeRF: Neural Radiance Fields from Blurry Imagescited by 179
  20. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  21. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  22. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  23. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  24. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 160
  25. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  26. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  27. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 152
  28. 2023SUDS: Scalable Urban Dynamic Scenescited by 151
  29. 2022SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fieldscited by 144
  30. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  31. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 132
  32. 2023Distilled Feature Fields Enable Few-Shot Language-Guided Manipulationcited by 130
  33. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 120
  34. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Modelscited by 120
  35. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  36. 2023S-NeRF: Neural Radiance Fields for Street Viewscited by 116
  37. 2021FENeRF: Face Editing in Neural Radiance Fieldscited by 112
  38. 2024textitS3Gaussian: Self-Supervised Street Gaussians for Autonomous Drivingcited by 105

50 most cited of 641 All 641 (JSON)