AI Paper Atlas

Research map / 3D vision / Face and shape

Coarse-to-fine Contrast: A Hybrid Self-supervised Method for Non-rigid 3D Shape Matching

Feifan Luo, Ting Li, Zhao Li, Hongyang Chen

ECCV 2026 · 3D vision › Face and shape · approach: Optimization-based shape matching

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 extrinsic (elastic basis) branch losses (ablation)Ours · TOPKIDSmean geodesic error (x100): 12.9 -> 4.9Improved
add extrinsic (elastic basis) branch losses (ablation)Ours · FAUST->SHREC'19mean geodesic error (x100): 4.3 -> 4.4No clear effect
add extrinsic orthogonality and bijectivity losses L_fmap (ablation)Ours · FAUST->SHREC'19mean geodesic error (x100): 5.3 -> 4.4Improved
add extrinsic orthogonality and bijectivity losses L_fmap (ablation)Ours · SMALmean geodesic error (x100): 3.6 -> 2.9Improved
add extrinsic contrastive energies (ablation)Ours · TOPKIDSmean geodesic error (x100): 11.3 -> 4.9Improved
add extrinsic contrastive energies (ablation)Ours · FAUST->SHREC'19mean geodesic error (x100): 4.8 -> 4.4Improved
add intrinsic contrastive energies (ablation)Ours · TOPKIDSmean geodesic error (x100): 26.8 -> 12.9Improved
add intrinsic contrastive energies (ablation)Ours · SMALmean geodesic error (x100): 5.3 -> 3.3Improved
add fine properness (spatial-spectral contrastive) lossULRSSM · FAUST->SHREC'19mean geodesic error (x100): 14.5 -> 7.1Improved
add fine properness (spatial-spectral contrastive) lossULRSSM · TOPKIDSmean geodesic error (x100): 9.4 -> 6.5Improved
add fine properness (spatial-spectral contrastive) lossULRSSM · SMALmean geodesic error (x100): 4.5 -> 4.6No clear effect
add spectral contrastive lossSURFMNet · TOPKIDSmean geodesic error (x100): 40.7 -> 21.1Improved

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