LoMa: Local Feature Matching Revisited
2026-04-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors revisit the problem of matching local features in images, which is important for 3D vision tasks like Structure-from-Motion. They improve performance by training on much larger and more diverse datasets, using bigger models and more computing power in their method called LoMa. They also create a new challenging dataset named HardMatch, with manually labeled ground truth, to better test feature matching methods. Their results show that LoMa performs much better than previous state-of-the-art methods across several benchmarks. The authors provide their code and models for others to use.
local feature matching3D visionStructure-from-Motiondatasetsmachine learningbenchmarkingground truthimage correspondencemodel scalingcomputer vision
Authors
David Nordström, Johan Edstedt, Georg Bökman, Jonathan Astermark, Anders Heyden, Viktor Larsson, Mårten Wadenbäck, Michael Felsberg, Fredrik Kahl
Abstract
Local feature matching has long been a fundamental component of 3D vision systems such as Structure-from-Motion (SfM), yet progress has lagged behind the rapid advances of modern data-driven approaches. The newer approaches, such as feed-forward reconstruction models, have benefited extensively from scaling dataset sizes, whereas local feature matching models are still only trained on a few mid-sized datasets. In this paper, we revisit local feature matching from a data-driven perspective. In our approach, which we call LoMa, we combine large and diverse data mixtures, modern training recipes, scaled model capacity, and scaled compute, resulting in remarkable gains in performance. Since current standard benchmarks mainly rely on collecting sparse views from successful 3D reconstructions, the evaluation of progress in feature matching has been limited to relatively easy image pairs. To address the resulting saturation of benchmarks, we collect 1000 highly challenging image pairs from internet data into a new dataset called HardMatch. Ground truth correspondences for HardMatch are obtained via manual annotation by the authors. In our extensive benchmarking suite, we find that LoMa makes outstanding progress across the board, outperforming the state-of-the-art method ALIKED+LightGlue by +18.6 mAA on HardMatch, +29.5 mAA on WxBS, +21.4 (1m, 10$^\circ$) on InLoc, +24.2 AUC on RUBIK, and +12.4 mAA on IMC 2022. We release our code and models publicly at https://github.com/davnords/LoMa.