AI Paper Atlas

Research map / 3D vision / Depth and stereo

iMatching: Imperative Correspondence Learning

Zitong Zhan, Dasong Gao, Yun-Jou Lin, Youjie Xia, Chen Wang

ECCV 2024 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 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
finetune CAPS with iMatching self-supervisionCAPS · TartanAir feature matchingMMA @1px: 26.9 -> 49.0Improved
finetune ASpanFormer with iMatchingASpanFormer · TartanAir feature matchingMMA @1px: 51.5 -> 58.4Improved
finetune poorly initialized Patch2Pix with iMatchingPatch2Pix · TartanAir feature matchingMMA @1px: 0.8 -> 7.1Improved
finetune DKM with iMatchingDKM · ETH3D-SLAM relative poseAUC@5deg: 58.2 -> 76.7Improved
train CAPS with SGP instead of iMatchingCAPS · ETH3D-SLAM relative poseAUC@5deg: 71.5 -> 70.9No clear effect
finetune CAPS with iMatchingCAPS · ETH3D-SLAM relative poseAUC@5deg: 71.5 -> 75.3Improved
finetune DKM with iMatching on KITTI360DKM · KITTI360 pose estimationAUC@5deg: 91.8 -> 92.6No clear effect
finetune ASpanFormer with iMatching on KITTI360ASpanFormer · KITTI360 pose estimationAUC@5deg: 74.4 -> 80.6Improved
add outlier rejection in bundle adjustment (ablation)iCAPS · TartanAir Oldtown EasyMMA @1px: 42.6 -> 59.2Improved
run more LM iterations in bundle adjustment (3 steps to full) (ablation)iCAPS · TartanAir SeasonForest EasyMMA @1px: 22.3 -> 29.4Improved
use own differentiable BA instead of COLMAP reconstruction for supervision (ablation)iCAPS · TartanAir Amusement EasyMMA @1px: 31.4 -> 59.7Improved

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