AI Paper Atlas

Research map / 3D vision / Depth and stereo

LoMa: Local Feature Matching Revisited

David Nordström, Johan Edstedt, Georg Bökman, Jonathan Astermark, Anders Heyden, Viktor Larsson, Mårten Wadenbäck, Michael Felsberg, Fredrik Kahl

ECCV 2026 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace ALIKED with DaD+DeDoDe and retrain on MegaDepth (ablation)LightGlue-style matcher · HardMatch (validation)mAA@10px: +5.7Improved
extend matcher and descriptor training data from MegaDepth to the full data mixture (ablation)LoMa · HardMatch (validation)mAA@10px: +9.1Improved
extend training from 50K to 250K steps (ablation)LoMa · HardMatch (validation)mAA@10px: +0.4Improved
scale matcher embedding dimension from 256 to 1024 (ablation)LoMa · HardMatch (validation)mAA@10px: +1.4Improved
use DaD detector rather than DISK for matching (ablation)LoMa · HardMatch (validation)mAA@10px: 45.3 -> 51.3Improved
specialize matcher on one detector instead of ensemble of detectors (ablation)LoMa with DaD · HardMatch (validation)mAA@10px: 51.0 -> 51.3Improved
increase keypoints from 512 to 4096 (ablation)LoMa-B · MegaDepth-1500AUC@20: 80.3 -> 83.6Improved
increase keypoints from 2048 to 4096 (ablation)SP+LG · MegaDepth-1500AUC@20: 76.4 -> 76.4No clear effect
train descriptor longer than 50K steps (ablation)LoMa descriptor · HardMatch (validation)validation lossHurt
replace ALIKED+LG with LoMa-Gsparse matcher · HardMatch (test)mAA@10px: 35.7 -> 54.3Improved
replace ALIKED+LG with LoMa-Gsparse matcher · WxBSmAA@10px: 43.9 -> 73.4Improved
replace ALIKED+LG with LoMa-Gsparse matcher · RUBIKAUC@10deg: 49.0 -> 73.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy