mlsanityData to 7 Oct 2026

BA-Net: Dense Bundle Adjustment Network

arXiv 1806.04807 ↗First posted 13 Jun 2018cs.CVcited by 173

Not on the map. Why?

Abstract (arXiv)

This paper introduces a network architecture to solve the structure-from-motion (SfM) problem via feature-metric bundle adjustment (BA), which explicitly enforces multi-view geometry constraints in the form of feature-metric error. The whole pipeline is differentiable so that the network can learn suitable features that make the BA problem more tractable. Furthermore, this work introduces a novel depth parameterization to recover dense per-pixel depth. The network first generates several basis depth maps according to the input image and optimizes the final depth as a linear combination of these basis depth maps via feature-metric BA. The basis depth maps generator is also learned via end-to-end training. The whole system nicely combines domain knowledge (i.e. hard-coded multi-view geometry constraints) and deep learning (i.e. feature learning and basis depth maps learning) to address the challenging dense SfM problem. Experiments on large scale real data prove the success of the proposed method.

Key facts. Cited by 173 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 30; 2023: 32; 2024: 29; 2025: 34; 2026: 19.

173 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  3. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  4. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  5. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  6. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  7. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  8. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  9. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  10. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  11. 2023Visual Geometry Grounded Deep Structure From Motioncited by 225
  12. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
38 more
  1. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  2. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 199
  3. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  4. 2022Deep Patch Visual Odometrycited by 186
  5. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  6. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  7. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 146
  8. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  9. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 129
  10. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 122
  11. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 107
  12. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  13. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  14. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  15. 2025Easi3R: Estimating Disentangled Motion from DUSt3R Without Trainingcited by 88
  16. 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memorycited by 82
  17. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 76
  18. 2024Large Spatial Model: End-to-end Unposed Images to Semantic 3Dcited by 73
  19. 2023Detector-Free Structure from Motioncited by 71
  20. 2021Monocular 3D Object Detection: An Extrinsic Parameter Free Approachcited by 69
  21. 2022Theseus: A Library for Differentiable Nonlinear Optimizationcited by 64
  22. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  23. 2023PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustmentcited by 62
  24. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  25. 2023DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fieldscited by 60
  26. 2022Motion Inspired Unsupervised Perception and Prediction in Autonomous Drivingcited by 59
  27. 2023Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedracited by 57
  28. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  29. 2025LONG3R: Long Sequence Streaming 3D Reconstructioncited by 45
  30. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  31. 2023Dense RGB SLAM with Neural Implicit Mapscited by 42
  32. 2021Tangent Space Backpropagation for 3D Transformation Groupscited by 40
  33. 2021Deep Two-View Structure-from-Motion Revisitedcited by 39
  34. 2021TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereocited by 39
  35. 2023R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Camerascited by 39
  36. 2022RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimizationcited by 38
  37. 2022A Benchmark and a Baseline for Robust Multi-view Depth Estimationcited by 38
  38. 2023Tracking and Mapping in Medical Computer Vision: A Reviewcited by 36

50 most cited of 173 All 173 (JSON)