Dense Match Summarization for Faster Two-view Estimation
Not on the map. Why?
Abstract (arXiv)
In this paper, we speed up robust two-view relative pose from dense correspondences. Previous work has shown that dense matchers can significantly improve both accuracy and robustness in the resulting pose. However, the large number of matches comes with a significantly increased runtime during robust estimation in RANSAC. To avoid this, we propose an efficient match summarization scheme which provides comparable accuracy to using the full set of dense matches, while having 10-100x faster runtime. We validate our approach on standard benchmark datasets together with multiple state-of-the-art dense matchers.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 39 references that are in the map. First posted on arXiv 3 Jun 2025.
Builds on
21 of 39 references.
References · 21
- 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
- 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
- 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
- 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
- 2024Grounding Image Matching in 3D with MASt3Rcited by 983
- 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
- 2023LightGlue: Local Feature Matching at Light Speedcited by 590
- 2024The Faiss librarycited by 376
- 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
- 2023RoMa: Robust Dense Feature Matchingcited by 302
- 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
- 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171
9 more
- 2018MAGSAC: marginalizing sample consensuscited by 123
- 2015WxBS: Wide Baseline Stereo Generalizationscited by 23
- 2023Two-View Geometry Scoring Without Correspondencescited by 11
- 2020P1AC: Revisiting Absolute Pose From a Single Affine Correspondencecited by 6
- 2021Space-Partitioning RANSACcited by 6
- 2021Adaptive Reordering Sampler with Neurally Guided MAGSACcited by 5
- 2017Accurate Motion Estimation through Random Sample Aggregated Consensuscited by 2
- 2018Latent RANSACcited by 2
- 2023Consensus-Adaptive RANSACcited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.
- 2025Robust Multi-view Camera Calibration from Dense Matches17 Dec 2025
- 2025Deep Learning Reforms Image Matching: A Survey and Outlook5 Jun 2025