# Dense Match Summarization for Faster Two-view Estimation

arXiv: https://arxiv.org/abs/2506.02893 · HTML: https://mlsanity.com/paper/2506.02893/

## 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 (most cited first, 21 of 21)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [COTR: Correspondence Transformer for Matching Across Images](https://mlsanity.com/paper/2103.14167/) (2021)
- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [MAGSAC: marginalizing sample consensus](https://mlsanity.com/paper/1803.07469/) (2018)
- [WxBS: Wide Baseline Stereo Generalizations](https://mlsanity.com/paper/1504.06603/) (2015)
- [Two-View Geometry Scoring Without Correspondences](https://mlsanity.com/paper/2306.01596/) (2023)
- [P1AC: Revisiting Absolute Pose From a Single Affine Correspondence](https://mlsanity.com/paper/2011.08790/) (2020)
- [Space-Partitioning RANSAC](https://mlsanity.com/paper/2111.12385/) (2021)
- [Adaptive Reordering Sampler with Neurally Guided MAGSAC](https://mlsanity.com/paper/2111.14093/) (2021)
- [Accurate Motion Estimation through Random Sample Aggregated Consensus](https://mlsanity.com/paper/1701.05268/) (2017)
- [Latent RANSAC](https://mlsanity.com/paper/1802.07045/) (2018)
- [Consensus-Adaptive RANSAC](https://mlsanity.com/paper/2307.14030/) (2023)

## Built on by (most cited first, 2 of 2)

- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Robust Multi-view Camera Calibration from Dense Matches](https://mlsanity.com/paper/2512.15608/) (2025)

## 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.