mlsanityData to 14 Oct 2026

PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment

arXiv 2306.15667 ↗First posted 27 Jun 2023cs.CVcited by 147

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Camera pose estimation is a long-standing computer vision problem that to date often relies on classical methods, such as handcrafted keypoint matching, RANSAC and bundle adjustment. In this paper, we propose to formulate the Structure from Motion (SfM) problem inside a probabilistic diffusion framework, modelling the conditional distribution of camera poses given input images. This novel view of an old problem has several advantages. (i) The nature of the diffusion framework mirrors the iterative procedure of bundle adjustment. (ii) The formulation allows a seamless integration of geometric constraints from epipolar geometry. (iii) It excels in typically difficult scenarios such as sparse views with wide baselines. (iv) The method can predict intrinsics and extrinsics for an arbitrary amount of images. We demonstrate that our method PoseDiffusion significantly improves over the classic SfM pipelines and the learned approaches on two real-world datasets. Finally, it is observed that our method can generalize across datasets without further training. Project page: https://posediffusion.github.io/

Key facts. Cited by 147 papers in the map (data through 14 Oct 2026). Builds on 42 of its 72 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

42 of 72 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  9. 2022Video Diffusion Modelscited by 2,305
  10. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  11. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  12. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
30 more
  1. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  2. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  3. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  4. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  5. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  6. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  7. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  8. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  9. 2016LIFT: Learned Invariant Feature Transformcited by 306
  10. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
  11. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  12. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 225
  13. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 201
  14. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  15. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  16. 2018BA-Net: Dense Bundle Adjustment Networkcited by 175
  17. 2017A Survey of Structure from Motioncited by 158
  18. 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 149
  19. 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
  20. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 112
  21. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  22. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  23. 20193DRegNet: A Deep Neural Network for 3D Point Registrationcited by 96
  24. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  25. 2023PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstructioncited by 84
  26. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  27. 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
  28. 2021Deep Two-View Structure-from-Motion Revisitedcited by 39
  29. 2022Virtual Correspondence: Humans as a Cue for Extreme-View Geometrycited by 25
  30. 20223DG-STFM: 3D Geometric Guided Student-Teacher Feature Matchingcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 42; 2025: 60; 2026: 37.

147 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  3. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  4. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  5. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  6. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 319
  7. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  8. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  9. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
  10. 2025Streaming 4D Visual Geometry Transformercited by 161
  11. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 141
  12. 2025MUSt3R: Multi-view Network for Stereo 3D Reconstructioncited by 141
38 more
  1. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  2. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 116
  3. 2025SpatialTrackerV2: 3D Point Tracking Made Easycited by 87
  4. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 82
  5. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 72
  6. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 67
  7. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  8. 2024Video-Guided Foley Sound Generation with Multimodal Controlscited by 49
  9. 2025Light3R-SfM: Towards Feed-forward Structure-from-Motioncited by 47
  10. 2025Dens3R: A Foundation Model for 3D Geometry Predictioncited by 46
  11. 2024FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstructioncited by 41
  12. 2025Matrix3D: Large Photogrammetry Model All-in-Onecited by 40
  13. 2025No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Viewscited by 40
  14. 2025AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesiscited by 39
  15. 2024SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Viewscited by 35
  16. 2025DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teacherscited by 32
  17. 2024Robust Incremental Structure-from-Motion with Hybrid Featurescited by 31
  18. 2024Reconstructing People, Places, and Camerascited by 31
  19. 2023Open-vocabulary object 6D pose estimationcited by 29
  20. 2025MP-SfM: Monocular Surface Priors for Robust Structure-from-Motioncited by 26
  21. 2026VGGT-Omegacited by 26
  22. 2025E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-trainingcited by 22
  23. 2025DVGT: Driving Visual Geometry Transformercited by 21
  24. 2025SAIL-Recon: Large SfM by Augmenting Scene Regression with Localizationcited by 20
  25. 2024SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wildcited by 18
  26. 2025One2Any: One-Reference 6D Pose Estimation for Any Objectcited by 18
  27. 2023DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fieldscited by 17
  28. 2025Quantized Visual Geometry Grounded Transformercited by 17
  29. 2024PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verifycited by 15
  30. 2023iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Viewscited by 14
  31. 2024Multiway Point Cloud Mosaicking with Diffusion and Global Optimizationcited by 14
  32. 2025DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusioncited by 14
  33. 2024FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimationcited by 12
  34. 2024Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Modelscited by 12
  35. 2025GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulationcited by 12
  36. 2024DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstructioncited by 11
  37. 2025Rig3R: Rig-Aware Conditioning for Learned 3D Reconstructioncited by 11
  38. 2023Learning Structure-from-Motion with Graph Attention Networkscited by 10

50 most cited of 147 All 147 (JSON)