mlsanityData to 14 Oct 2026

Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimates

arXiv 2602.18906 ↗First posted 21 Feb 2026cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Structure-from-Motion (SfM) is a fundamental 3D vision task for recovering camera parameters and scene geometry from multi-view images. While recent deep learning advances enable accurate Monocular Depth Estimation (MDE) from single images without depending on camera motion, integrating MDE into SfM remains a challenge. Unlike conventional triangulated sparse point clouds, MDE produces dense depth maps with significantly higher error variance. Inspired by modern RANSAC estimators, we propose Marginalized Bundle Adjustment (MBA) to mitigate MDE error variance leveraging its density. With MBA, we show that MDE depth maps are sufficiently accurate to yield SoTA or competitive results in SfM and camera relocalization tasks. Through extensive evaluations, we demonstrate consistently robust performance across varying scales, ranging from few-frame setups to large multi-view systems with thousands of images. Our method highlights the significant potential of MDE in multi-view 3D vision.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 66 of its 84 references that are in the map. First posted on arXiv 21 Feb 2026.

Builds on

66 of 84 references.

References · 66

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  4. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  5. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  7. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  8. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  9. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  10. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  12. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
38 more
  1. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  2. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  3. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  4. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  5. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
  6. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 382
  7. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  8. 2023RoMa: Robust Dense Feature Matchingcited by 302
  9. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 299
  10. 20243D Reconstruction with Spatial Memorycited by 277
  11. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 261
  12. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  13. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  14. 2024Global Structure-from-Motion Revisitedcited by 218
  15. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  16. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  17. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  18. 2020Robust Consistent Video Depth Estimationcited by 188
  19. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 177
  20. 2020Visual Camera Re-Localization from RGB and RGB-D Images Using DSACcited by 176
  21. 2018BA-Net: Dense Bundle Adjustment Networkcited by 175
  22. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
  23. 2019MAGSAC++, a fast, reliable and accurate robust estimatorcited by 161
  24. 2016Deep Image Retrieval: Learning global representations for image searchcited by 147
  25. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 147
  26. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 136
  27. 2018MAGSAC: marginalizing sample consensuscited by 123
  28. 2021Capturing, Reconstructing, and Simulating: the UrbanScene3D Datasetcited by 118
  29. 2021NeRF for Outdoor Scene Relightingcited by 114
  30. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 114
  31. 2023Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Posescited by 107
  32. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 102
  33. 2019Hierarchical Scene Coordinate Classification and Regression for Visual Localizationcited by 93
  34. 2023VR-NeRF: High-Fidelity Virtualized Walkable Spacescited by 86
  35. 2022DFNet: Enhance Absolute Pose Regression with Direct Feature Matchingcited by 82
  36. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  37. 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
  38. 2023Detector-Free Structure from Motioncited by 71

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depthcited by 0
  2. 2026GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assemblycited by 0
  3. 2026Triangulation-Free Bundle Adjustment with Graduated Non-Convexity for Camera Pose Refinement from Coarse Priorscited by 0