AI Paper Atlas

Research map / 3D vision / Depth and stereo

Guiding Local Feature Matching with Surface Curvature

Shuzhe Wang, Juho Kannala, Marc Pollefeys, Daniel Barath

ICCV 2023 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 6 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 curvature similarity extractor (CSE) with fine-tuning to QuadTreeQuadTree · ScanNetAUC@5: 24.9 -> 25.8Improved
add CSE to SuperGlue without fine-tuningSuperGlue · MegaDepth-1500AUC@5: 43.7 -> 46.2Improved
add CSE to SP+SG for visual localizationSuperPoint + SuperGlue · Aachen Day-Night Night (0.25m, 2deg)pose recall (%): 77.0 -> 75.9Hurt
add CSE to SP+SG for visual localizationSuperPoint + SuperGlue · Aachen Day-Night Day (0.25m, 2deg)pose recall (%): 89.8 -> 90.7Improved
fine-tune depth predictor with matching loss on top of CSE (ablation)QuadTree + CSE · ScanNetAUC@5: 25.2 -> 25.8Improved
use multi-scale curvature extraction (ablation)QuadTree + CSE · ScanNetAUC@5: 25.2 -> 25.6; time 112 -> 338 msMixed
replace ViT MiDaS depth predictor with lightweight MiDaS (Real-time) (ablation)QuadTree + CSE · ScanNetAUC@5: 25.8 -> 25.5No clear effect
use ground-truth depth instead of fine-tuned predicted depth (ablation)QuadTree + CSE · ScanNetAUC@5: 25.8 -> 25.1Hurt
replace quadric (ellipse) fitting with surface fitting for curvature (ablation)QuadTree + CSE · ScanNetAUC@5: 25.8 -> 24.8Hurt
set mixing weight lambda lower than 0.8-0.9 (ablation)QuadTree + CSE · ScanNetAUC@5: 26.1 -> 17.8 (lambda 0.8 to 0.3)Hurt

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