AI Paper Atlas

Research map / 3D vision / Depth and stereo

Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching

Xiaoyong Lu, Songlin Du

ECCV 2024 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 11 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 one-to-one with many-to-one coarse matching (ablation)RCM semi-sparse matcher · MegaDepth ablation#Matches: 507.8 -> 770.7 (+51.8%)Improved
replace one-to-one with many-to-one coarse matching (ablation)RCM semi-sparse matcher · MegaDepth ablationprecision: 94.2 -> 97.2Improved
add dynamic view switcher (ablation)RCM semi-sparse matcher · MegaDepth ablation#Matches: 770.7 -> 951.4 (+23.4%)Improved
add U-Net feature extraction (ablation)semi-sparse baseline · MegaDepth ablation#Matches: 492.3 -> 507.8Improved
raise coarse resolution from 1/16 to 1/8 (ablation)RCM · MegaDepth ablation#Matches: 951.4 -> 961.4Improved
remove view switcher on extreme-scale pairs (ablation)RCM · extreme-scale MegaDepth#Matches: 887 -> 653Hurt
flip the switcher decision so small-scale image is source (ablation)RCM · extreme-scale MegaDepth#Matches: 887 -> 76Hurt
use semi-sparse sampling instead of keypoints in both images (sparse) (ablation)baseline matcher · MegaDepth ablationprecision: 98.0 -> 93.7Hurt
dense sampling vs sparse sampling for coarse features (ablation)baseline matcher · MegaDepth ablation#Matches: 451.7 -> 932.1Mixed
RCM vs LoFTR on ScanNet pose (zero-shot)RCM · ScanNet pose estimation (zero-shot from MegaDepth)AUC@10deg: 33.6 -> 34.6Improved
RCM vs RoMa on MegaDepth poseRCM · MegaDepth pose estimationAUC@10deg: 69.4 vs 76.9Hurt

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