AI Paper Atlas

Research map / 3D vision / Depth and stereo

COTR: Correspondence Transformer for Matching Across Images

Wei Jiang, Eduard Trulls, Jan Hosang, Andrea Tagliasacchi, Kwang Moo Yi

ICCV 2021 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 314 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 transformer with MLP variant (ablation)COTR · IMC2020 / MegaDepth warpingdense correspondence qualityImproved
add recursive zoom-in (four steps, factor 2) (ablation)COTR · HPatchespixel error distributionImproved
add filtering of erroneous correspondences (ablation)COTR · ETH3DAEPE: roughly 5% relativeImproved
use linear positional-encoding frequency instead of log-linear (ablation)COTR · MegaDepth trainingtraining loss convergenceImproved
add dense interpolation instead of querying only sparse pointsCOTR · KITTI-2015AEPE: 2.62 -> 6.12Hurt
add dense interpolationCOTR · KITTI-2012Fl (%): 7.36 -> 10.50Hurt
add dense interpolationCOTR · HPatchesPCK-5px: 91.10 -> 86.33Hurt
increase number of matches per image pair N from 128 to 2048COTR+DEGENSAC · IMC2020 stereomAA(5deg): 0.356 -> 0.444Improved
COTR instead of RAFT with DEGENSACpose estimation · IMC2020 stereomAA(5deg): 0.163 -> 0.515Improved
COTR instead of RAFTflow estimation · ETH3D (rate=15)AEPE: 13.74 -> 2.61Improved
COTR instead of RAFTflow estimation · KITTI-2015AEPE: 5.04 -> 2.62Improved
COTR instead of GLU-Net+GOCorflow estimation · HPatchesAEPE: 20.16 -> 7.75Improved

Later papers that compared with this method

10 later accepted papers report COTR as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.

2 more not listed.

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