AI Paper Atlas

Research map / 3D vision / Depth and stereo

LightGlue: Local Feature Matching at Light Speed

Philipp Lindenberger, Paul-Edouard Sarlin, Marc Pollefeys

ICCV 2023 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 1,188 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
add matchability classifier (disentangle similarity and matchability) (ablation)LightGlue · Synthetic homographiesprecision (%): 67.4 -> 86.8Improved
use rotary relative positional encoding instead of absolute (ablation)LightGlue · Synthetic homographiesprecision (%): 84.2 -> 86.8Improved
use bidirectional cross-attention instead of full cross-attention (ablation)LightGlue · Synthetic homographiesrun time (ms): 22.8 -> 19.4 ms, precision 86.6 vs 86.8Improved
add deep supervision so earlier layers predict matches (ablation)LightGlue · Synthetic homographiesrecall (%): >90% recall after 5 layersImproved
add adaptive depth and width (ablation)LightGlue · MegaDepth-1500 (SuperPoint, RANSAC)time (ms): 44.2 -> 31.4 ms, AUC@5 49.9 -> 49.4Improved
adaptive depth and width on easy vs hard pairs (ablation)LightGlue · MegaDepth pairs by overlapspeedup over non-adaptive: 1.86 (easy) vs 1.16 (hard)Mixed
replace SuperGlue with LightGlueSuperPoint matching · Aachen Day-Nightpairs per second: 6.5 -> 17.2Improved
replace SuperGlue with LightGlueSuperPoint matching · Synthetic homographiesprecision (%): 74.6 -> 86.8Improved
replace SuperGlue with LightGlueSuperPoint matching · MegaDepth-1500 RANSAC AUC@5pose AUC @5deg: 49.7 -> 49.9No clear effect
use DISK features with LightGlue instead of SuperPointLightGlue · IMC 2020 stereo AUC@5AUC @5deg: 59.03 -> 67.02Improved
use LightGlue instead of dense ASpanFormerfeature matching · MegaDepth-1500 RANSAC AUC@5pose AUC @5deg: 55.3 -> 49.9Hurt

Later papers that compared with this method

6 later accepted papers report LightGlue as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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