mlsanityData to 14 Oct 2026

MAGSAC++, a fast, reliable and accurate robust estimator

arXiv 1912.05909 ↗First posted 11 Dec 2019cs.CVcited by 161

Not on the map. Why?

Abstract (arXiv)

A new method for robust estimation, MAGSAC++, is proposed. It introduces a new model quality (scoring) function that does not require the inlier-outlier decision, and a novel marginalization procedure formulated as an iteratively re-weighted least-squares approach. We also propose a new sampler, Progressive NAPSAC, for RANSAC-like robust estimators. Exploiting the fact that nearby points often originate from the same model in real-world data, it finds local structures earlier than global samplers. The progressive transition from local to global sampling does not suffer from the weaknesses of purely localized samplers. On six publicly available real-world datasets for homography and fundamental matrix fitting, MAGSAC++ produces results superior to state-of-the-art robust methods. It is faster, more geometrically accurate and fails less often.

Key facts. Cited by 161 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 16; 2023: 31; 2024: 30; 2025: 36; 2026: 34.

161 papers.

Sort:

By area:

  1. 2023RoMa: Robust Dense Feature Matchingcited by 302
  2. 2024Global Structure-from-Motion Revisitedcited by 218
  3. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
  4. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 114
  5. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  6. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 82
  7. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 63
  8. 2022MeshLoc: Mesh-Based Visual Localizationcited by 62
  9. 2024GLACE: Global Local Accelerated Coordinate Encodingcited by 48
  10. 2024DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detectorcited by 39
  11. 2023SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understandingcited by 38
  12. 2023Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairscited by 37
38 more
  1. 2022Generalized Differentiable RANSACcited by 30
  2. 2023SGAligner : 3D Scene Alignment with Scene Graphscited by 30
  3. 2021Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlationcited by 28
  4. 2021Self-supervised Geometric Perceptioncited by 26
  5. 2022ReDFeat: Recoupling Detection and Description for Multimodal Feature Learningcited by 26
  6. 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
  7. 2025Emergent Outlier View Rejection in Visual Geometry Grounded Transformerscited by 22
  8. 2023Steerers: A framework for rotation equivariant keypoint descriptorscited by 21
  9. 2023Visual Localization using Imperfect 3D Models from the Internetcited by 20
  10. 2021Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimationcited by 17
  11. 2021VSAC: Efficient and Accurate Estimator for H and Fcited by 17
  12. 2025R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localizationcited by 17
  13. 2022A Hybrid Quantum-Classical Algorithm for Robust Fittingcited by 16
  14. 2022ARCS: Accurate Rotation and Correspondence Searchcited by 15
  15. 2023A Large Scale Homography Benchmarkcited by 15
  16. 2023Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registrationcited by 15
  17. 2025Convex Relaxation for Robust Vanishing Point Estimation in Manhattan Worldcited by 15
  18. 2025Co-op: Correspondence-based Novel Object Pose Estimationcited by 14
  19. 2024Learning to Make Keypoints Sub-Pixel Accuratecited by 13
  20. 2026Advances in Global Solvers for 3D Visioncited by 13
  21. 2024FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimationcited by 12
  22. 2025LiftFeat: 3D Geometry-Aware Local Feature Matchingcited by 12
  23. 2023Two-View Geometry Scoring Without Correspondencescited by 11
  24. 2026LoMa: Local Feature Matching Revisitedcited by 11
  25. 2021On the Instability of Relative Pose Estimation and RANSAC's Rolecited by 10
  26. 2022ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretizationcited by 10
  27. 2022A New Outlier Removal Strategy Based on Reliability of Correspondence Graph for Fast Point Cloud Registrationcited by 10
  28. 2023GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learningcited by 10
  29. 2023IMP: Iterative Matching and Pose Estimation with Adaptive Poolingcited by 10
  30. 2024MGNet: Learning Correspondences via Multiple Graphscited by 10
  31. 2024Learning to Produce Semi-dense Correspondences for Visual Localizationcited by 10
  32. 2022NeFSAC: Neurally Filtered Minimal Samplescited by 9
  33. 2023Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Directioncited by 9
  34. 2024Differentiable Product Quantization for Memory Efficient Camera Relocalizationcited by 9
  35. 2025A Guide to Structureless Visual Localizationcited by 9
  36. 2021Finding Geometric Models by Clustering in the Consensus Spacecited by 8
  37. 2023VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruningcited by 8
  38. 2024CLIP-Loc: Multi-modal Landmark Association for Global Localization in Object-based Mapscited by 8

50 most cited of 161 All 161 (JSON)