mlsanityData to 7 Oct 2026

Global Structure-from-Motion Revisited

arXiv 2407.20219 ↗First posted 29 Jul 2024cs.CVcited by 215

Not on the map. Why?

Abstract (arXiv)

Recovering 3D structure and camera motion from images has been a long-standing focus of computer vision research and is known as Structure-from-Motion (SfM). Solutions to this problem are categorized into incremental and global approaches. Until now, the most popular systems follow the incremental paradigm due to its superior accuracy and robustness, while global approaches are drastically more scalable and efficient. With this work, we revisit the problem of global SfM and propose GLOMAP as a new general-purpose system that outperforms the state of the art in global SfM. In terms of accuracy and robustness, we achieve results on-par or superior to COLMAP, the most widely used incremental SfM, while being orders of magnitude faster. We share our system as an open-source implementation at {https://github.com/colmap/glomap}.

Key facts. Cited by 215 papers in the map (data through 7 Oct 2026). Builds on 26 of its 83 references that are in the map. First posted on arXiv 29 Jul 2024.

Builds on

26 of 83 references.

References · 26

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  3. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  4. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  5. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  6. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  7. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 199
  8. 2019MAGSAC++, a fast, reliable and accurate robust estimatorcited by 160
  9. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 129
  10. 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 98
  11. 2023Detector-Free Structure from Motioncited by 71
  12. 2020Shonan Rotation Averaging: Global Optimality by Surfing SO(p)ncited by 46
14 more
  1. 2014Robust Camera Location Estimation by Convex Programmingcited by 41
  2. 2019NeuRoRA: Neural Robust Rotation Averagingcited by 32
  3. 2023Doppelgangers: Learning to Disambiguate Images of Similar Structurescited by 32
  4. 2019Baseline Desensitizing In Translation Averagingcited by 27
  5. 2021A Pose-only Solution to Visual Reconstruction and Navigationcited by 20
  6. 2018Convex Relaxations for Pose Graph Optimization with Outlierscited by 19
  7. 2019Algebraic Characterization of Essential Matrices and Their Averaging in Multiview Settingscited by 18
  8. 2023Revisiting Rotation Averaging: Uncertainties and Robust Lossescited by 18
  9. 2018GPSfM: Global Projective SFM Using Algebraic Constraints on Multi-View Fundamental Matricescited by 14
  10. 2020Reducing Drift in Structure From Motion Using Extended Featurescited by 10
  11. 2015Linear Global Translation Estimation with Feature Trackscited by 9
  12. 2023Rotation Synchronization via Deep Matrix Factorizationcited by 7
  13. 2022Absolute Triangulation Algorithms for Space Explorationcited by 5
  14. 2015On Computing the Translations Norm in the Epipolar Graphcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 106; 2026: 101.

215 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  2. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  3. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  4. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 292
  5. 2025ReCamMaster: Camera-Controlled Generative Rendering from A Single Videocited by 278
  6. 20243D Reconstruction with Spatial Memorycited by 269
  7. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  8. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  9. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 130
  10. 2025GameFactory: Creating New Games with Generative Interactive Videoscited by 124
  11. 2024CamI2V: Camera-Controlled Image-to-Video Diffusion Modelcited by 115
  12. 2025Aether: Geometric-Aware Unified World Modelingcited by 94
38 more
  1. 2025Easi3R: Estimating Disentangled Motion from DUSt3R Without Trainingcited by 88
  2. 2025MegaLoc: One Retrieval to Place Them Allcited by 58
  3. 2025RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Controlcited by 54
  4. 2025Light3R-SfM: Towards Feed-forward Structure-from-Motioncited by 47
  5. 2025FullDiT: Multi-Task Video Generative Foundation Model with Full Attentioncited by 45
  6. 2025AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesiscited by 39
  7. 2025FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesiscited by 37
  8. 2026LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstructioncited by 32
  9. 2025Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigationcited by 30
  10. 2025Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Videocited by 27
  11. 2025Dynamic Camera Poses and Where to Find Themcited by 26
  12. 2025MP-SfM: Monocular Surface Priors for Robust Structure-from-Motioncited by 25
  13. 2026Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstructioncited by 25
  14. 2026ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Trainingcited by 23
  15. 2025Block-Sparse Global Attention for Efficient Multi-View Geometry Transformerscited by 22
  16. 2026VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstructioncited by 22
  17. 2025iLRM: An Iterative Large 3D Reconstruction Modelcited by 18
  18. 2025SAIL-Recon: Large SfM by Augmenting Scene Regression with Localizationcited by 18
  19. 2024AKiRa: Augmentation Kit on Rays for optical video generationcited by 17
  20. 2025AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibrationcited by 17
  21. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 16
  22. 2025Dense-SfM: Structure from Motion with Dense Consistent Matchingcited by 15
  23. 2025FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attentioncited by 15
  24. 2025AVGGT: Rethinking Global Attention for Accelerating VGGTcited by 15
  25. 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memoriescited by 15
  26. 2026Vista4D: Video Reshooting with 4D Point Cloudscited by 15
  27. 2026VGG-T3: Offline Feed-Forward 3D Reconstruction at Scalecited by 14
  28. 2025ViSTA-SLAM: Visual SLAM with Symmetric Two-view Associationcited by 13
  29. 2025DaD: Distilled Reinforcement Learning for Diverse Keypoint Detectioncited by 12
  30. 2025Dynamic View Synthesis as an Inverse Problemcited by 12
  31. 2025Benchmarking Egocentric Visual-Inertial SLAM at City Scalecited by 12
  32. 2026Advances in Global Solvers for 3D Visioncited by 12
  33. 2025GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulationcited by 11
  34. 20253R-GS: Best Practice in Optimizing Camera Poses Along with 3DGScited by 10
  35. 2026tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstructioncited by 10
  36. 2025The Coralscapes Dataset: Semantic Scene Understanding in Coral Reefscited by 9
  37. 2025Regist3R: Incremental Registration with Stereo Foundation Modelcited by 9
  38. 2025A Guide to Structureless Visual Localizationcited by 9

50 most cited of 215 All 215 (JSON)