AI Paper Atlas

Research map / Detection and segmentation / CNN features

ECO-TR: Efficient Correspondences Finding via Coarse-to-Fine Refinement

Dongli Tan, Jiang-Jiang Liu, Xingyu Chen, Chao Chen, Ruixin Zhang, Yunhang Shen, Shouhong Ding, Rongrong Ji

ECCV 2022 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 23 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 middle stage to coarse-only model (ablation)ECO-TR · ETH3D rate=15AEPE: 9.19 -> 3.83Improved
add fine stage to coarse+middle model (ablation)ECO-TR · ETH3D rate=15AEPE: 3.83 -> 2.72Improved
add deep supervision of middle and fine branches during training (ablation)ECO-TR · ETH3D rate=15AEPE: 9.53 -> 9.19Improved
use adaptive query-clustering instead of GRID clustering (ablation)ECO-TR · ETH3D rate=15AEPE: 3.10 -> 2.72Improved
use adaptive query-clustering instead of GRID clustering (ablation)ECO-TR · ETH3D rate=3AEPE: 1.64 -> 1.53Improved
replace full attention with linear transformer in middle and fine stages (ablation)ECO-TR · ETH3D rate=3AEPE: 1.53 -> 1.55Hurt
use uncertainty filter instead of cycle consistency filter (ablation)ECO-TR · ETH3D rate=15AEPE: 2.45 -> 2.08Improved
combine uncertainty and cycle consistency filtering (ablation)ECO-TR · ETH3D rate=15AEPE: 2.08 -> 2.06Improved
end-to-end feature-level cropping vs recursive zoom-in of COTR (10k queries)ECO-TR · 10k queriesinference time (sec): 433.53 -> 2.35Improved
ECO-TR vs COTR on HPatches (sampled matches)ECO-TR · HPatchesPCK-5px: 90.85 -> 90.71Hurt
ECO-TR vs COTR on KITTI-2015ECO-TR · KITTI-2015AEPE: 2.06 -> 1.40Improved
ECO-TR vs COTR on MegaDepth with 300 matchesECO-TR · MegaDepth St. Paul's (N=300)mAA@5deg: 0.434 -> 0.430No clear effect

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