mlsanityData to 14 Oct 2026

DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields

arXiv 2303.14478 ↗First posted 25 Mar 2023cs.CVcited by 60

Not on the map. Why?

Abstract (arXiv)

Recent works such as BARF and GARF can bundle adjust camera poses with neural radiance fields (NeRF) which is based on coordinate-MLPs. Despite the impressive results, these methods cannot be applied to Generalizable NeRFs (GeNeRFs) which require image feature extractions that are often based on more complicated 3D CNN or transformer architectures. In this work, we first analyze the difficulties of jointly optimizing camera poses with GeNeRFs, and then further propose our DBARF to tackle these issues. Our DBARF which bundle adjusts camera poses by taking a cost feature map as an implicit cost function can be jointly trained with GeNeRFs in a self-supervised manner. Unlike BARF and its follow-up works, which can only be applied to per-scene optimized NeRFs and need accurate initial camera poses with the exception of forward-facing scenes, our method can generalize across scenes and does not require any good initialization. Experiments show the effectiveness and generalization ability of our DBARF when evaluated on real-world datasets. Our code is available at urlhttps://aibluefisher.github.io/dbarf.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). Builds on 44 of its 59 references that are in the map. First posted on arXiv 25 Mar 2023.

Builds on

44 of 59 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  9. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  10. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  11. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  12. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
32 more
  1. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  2. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  3. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  4. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  5. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  6. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  7. 2020Neural Sparse Voxel Fieldscited by 959
  8. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  9. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  10. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  11. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  12. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  13. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  14. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  15. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  16. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  17. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
  18. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  19. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  20. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 196
  21. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  22. 2018BA-Net: Dense Bundle Adjustment Networkcited by 175
  23. 2021NeRF--: Neural Radiance Fields Without Known Camera Parameterscited by 155
  24. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  25. 2022Generalizable Patch-Based Neural Renderingcited by 122
  26. 2021Light Field Neural Renderingcited by 108
  27. 2022GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimationcited by 86
  28. 2022SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstructioncited by 49
  29. 2019NeuRoRA: Neural Robust Rotation Averagingcited by 32
  30. 2019Graph-Based Parallel Large Scale Structure from Motioncited by 21
  31. 2022VMRF: View Matching Neural Radiance Fieldscited by 17
  32. 2022Robustifying the Multi-Scale Representation of Neural Radiance Fieldscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 10; 2024: 28; 2025: 17; 2026: 5.

60 papers.

Sort:

By area:

  1. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  2. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  3. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 161
  4. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 72
  5. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 62
  6. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  7. 2023CamP: Camera Preconditioning for Neural Radiance Fieldscited by 55
  8. 2024DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensuscited by 51
  9. 2024SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splattingcited by 42
  10. 2025No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Viewscited by 40
  11. 2023FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flowcited by 39
  12. 2023Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairscited by 37
38 more
  1. 20254DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Videocited by 27
  2. 2025E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-trainingcited by 22
  3. 2023DReg-NeRF: Deep Registration for Neural Radiance Fieldscited by 21
  4. 2024Neural Fields in Robotics: A Surveycited by 21
  5. 2024MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Datacited by 21
  6. 2024GGRt: Towards Pose-free Generalizable 3D Gaussian Splatting in Real-timecited by 20
  7. 2024VDG: Vision-Only Dynamic Gaussian for Driving Simulationcited by 16
  8. 2025VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Framescited by 15
  9. 2025True Self-Supervised Novel View Synthesis is Transferablecited by 15
  10. 2026TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstructioncited by 14
  11. 2025RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registrationcited by 13
  12. 2024Neural Radiance Field-based Visual Rendering: A Comprehensive Reviewcited by 12
  13. 2024TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Trackscited by 12
  14. 2023CBARF: Cascaded Bundle-Adjusting Neural Radiance Fields from Imperfect Camera Posescited by 11
  15. 2024ZeroGS: Training 3D Gaussian Splatting from Unposed Imagescited by 10
  16. 2024Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priorscited by 8
  17. 2025SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Viewscited by 7
  18. 2024Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAMcited by 6
  19. 2024CrossScore: Towards Multi-View Image Evaluation and Scoringcited by 6
  20. 2024GeoNLF: Geometry guided Pose-Free Neural LiDAR Fieldscited by 6
  21. 2024Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenescited by 6
  22. 2023MC-NeRF: Multi-Camera Neural Radiance Fields for Multi-Camera Image Acquisition Systemscited by 5
  23. 2023BASED: Bundle-Adjusting Surgical Endoscopic Dynamic Video Reconstruction using Neural Radiance Fieldscited by 5
  24. 2024Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinementcited by 5
  25. 2024Invertible Neural Warp for NeRFcited by 5
  26. 2023AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimizationcited by 4
  27. 2023SCALAR-NeRF: SCAlable LARge-scale Neural Radiance Fields for Scene Reconstructioncited by 4
  28. 2023Continuous Pose for Monocular Cameras in Neural Implicit Representationcited by 4
  29. 2024URS-NeRF: Unordered Rolling Shutter Bundle Adjustment for Neural Radiance Fieldscited by 4
  30. 2025SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Imagescited by 4
  31. 2025EA3D: Online Open-World 3D Object Extraction from Streaming Videoscited by 4
  32. 2024SUP-NeRF: A Streamlined Unification of Pose Estimation and NeRF for Monocular 3D Object Reconstructioncited by 3
  33. 2025Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representationscited by 3
  34. 2024ID-NeRF: Indirect Diffusion-guided Neural Radiance Fields for Generalizable View Synthesiscited by 2
  35. 2025NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitivescited by 2
  36. 20243D Reconstruction and New View Synthesis of Indoor Environments based on a Dual Neural Radiance Fieldcited by 1
  37. 2024DynSUP: Dynamic Gaussian Splatting from An Unposed Image Paircited by 1
  38. 2025Coca-Splat: Collaborative Optimization for Camera Parameters and 3D Gaussianscited by 1

50 most cited of 60 All 60 (JSON)