# MODS: Fast and Robust Method for Two-View Matching

arXiv: https://arxiv.org/abs/1503.02619 · HTML: https://mlsanity.com/paper/1503.02619/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2015.

## Built on by (most cited first, 26 of 26)

- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Correlation Verification for Image Retrieval](https://mlsanity.com/paper/2204.01458/) (2022)
- [Generalized Differentiable RANSAC](https://mlsanity.com/paper/2212.13185/) (2022)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [VSAC: Efficient and Accurate Estimator for H and F](https://mlsanity.com/paper/2106.10240/) (2021)
- [A Large Scale Homography Benchmark](https://mlsanity.com/paper/2302.09997/) (2023)
- [ScaleNet: A Shallow Architecture for Scale Estimation](https://mlsanity.com/paper/2112.04846/) (2021)
- [SIFT Matching by Context Exposed](https://mlsanity.com/paper/2106.09584/) (2021)
- [Space-Partitioning RANSAC](https://mlsanity.com/paper/2111.12385/) (2021)
- [Relative Pose from SIFT Features](https://mlsanity.com/paper/2203.07930/) (2022)
- [Handbook on Leveraging Lines for Two-View Relative Pose Estimation](https://mlsanity.com/paper/2309.16040/) (2023)
- [HarrisZ^+: Harris Corner Selection for Next-Gen Image Matching Pipelines](https://mlsanity.com/paper/2109.12925/) (2021)
- [Adaptive Reordering Sampler with Neurally Guided MAGSAC](https://mlsanity.com/paper/2111.14093/) (2021)
- [Image Matching by Bare Homography](https://mlsanity.com/paper/2305.08946/) (2023)
- [Image Matching Filtering and Refinement by Planes and Beyond](https://mlsanity.com/paper/2411.09484/) (2024)
- [Learning Affine Correspondences by Integrating Geometric Constraints](https://mlsanity.com/paper/2504.04834/) (2025)
- [RLSAC: Reinforcement Learning enhanced Sample Consensus for End-to-End Robust Estimation](https://mlsanity.com/paper/2308.05318/) (2023)
- [Method Towards CVPR 2021 Image Matching Challenge](https://mlsanity.com/paper/2108.04453/) (2021)
- [Controllable RANSAC-based Anomaly Detection via Hypothesis Testing](https://mlsanity.com/paper/2410.15133/) (2024)
- [USACv20: robust essential, fundamental and homography matrix estimation](https://mlsanity.com/paper/2104.05044/) (2021)
- [Feature Point Extraction for Extra-Affine Image](https://mlsanity.com/paper/2503.03479/) (2025)
- [Cross-View Localization via Redundant Sliced Observations and A-Contrario Validation](https://mlsanity.com/paper/2508.05369/) (2025)
- [Understanding and Optimizing Attention-Based Sparse Matching for Diverse Local Features](https://mlsanity.com/paper/2602.08430/) (2026)
- [3D Reconstruction from public webcams](https://mlsanity.com/paper/2108.09476/) (2021)
- [Matching with AffNet based rectifications](https://mlsanity.com/paper/2207.14660/) (2022)
- [LoCUS: Learning Multiscale 3D-consistent Features from Posed Images](https://mlsanity.com/paper/2310.01095/) (2023)

## Abstract (arXiv)

A novel algorithm for wide-baseline matching called MODS - Matching On Demand with view Synthesis - is presented. The MODS algorithm is experimentally shown to solve a broader range of wide-baseline problems than the state of the art while being nearly as fast as standard matchers on simple problems. The apparent robustness vs. speed trade-off is finessed by the use of progressively more time-consuming feature detectors and by on-demand generation of synthesized images that is performed until a reliable estimate of geometry is obtained. We introduce an improved method for tentative correspondence selection, applicable both with and without view synthesis. A modification of the standard first to second nearest distance rule increases the number of correct matches by 5-20% at no additional computational cost. Performance of the MODS algorithm is evaluated on several standard publicly available datasets, and on a new set of geometrically challenging wide baseline problems that is made public together with the ground truth. Experiments show that the MODS outperforms the state-of-the-art in robustness and speed. Moreover, MODS performs well on other classes of difficult two-view problems like matching of images from different modalities, with wide temporal baseline or with significant lighting changes.