AI Paper Atlas

Research map / 3D vision / Face and shape

Universal 3D Shape Matching via Coarse-to-Fine Language Guidance

Qinfeng Xiao, Guofeng Mei, Bo Yang, Liying Zhang, Jian Zhang, Kit-lun Yick

CVPR 2026 · 3D vision › Face and shape · approach: Optimization-based shape matching · 1 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 semantic feature fields (SD-DINO) to geometric features (ablation)UniMatch · SNIS (inter-class)average geodesic error: 0.49 -> 0.22Improved
Add group-wise rank-based contrastive loss (ablation)UniMatch · SNIS (inter-class)average geodesic error: 0.22 -> 0.19Improved
Add group-wise rank-based contrastive loss (ablation)UniMatch · TOSCA (inter-class)average geodesic error: 0.26 -> 0.23Improved
Use group-wise RnC loss instead of SupCon loss with pseudo positives (ablation)UniMatch · TOSCA (inter-class)average geodesic error: 0.29 -> 0.23Improved
Use FG-CLIP instead of CLIP language embeddings (ablation)UniMatch · TOSCA (inter-class)average geodesic error: 0.26 -> 0.23Improved
Use FG-CLIP instead of SigLip language embeddings (ablation)UniMatch · TOSCA (inter-class)average geodesic error: 0.24 -> 0.23No clear effect
Use FG-CLIP instead of CLIP on SHREC07 (ablation)UniMatch · SHREC07 (inter-class)average geodesic error: 0.37 -> 0.37No clear effect
Replace DenseMatcher with UniMatch on non-isometric SMALUniMatch · SMAL (non-isometric)average geodesic error (x100): 4.7 -> 4.8No clear effect
Replace DenseMatcher with UniMatch on TOPKIDSUniMatch · TOPKIDS (non-isometric)average geodesic error (x100): 6.2 -> 5.9Improved
UniMatch versus URSSM on near-isometric FAUSTUniMatch · FAUST (near-isometric)average geodesic error (x100): 1.6 -> 1.6No clear effect
UniMatch versus DenseMatcher on SHREC19UniMatch · SHREC19 (near-isometric)average geodesic error (x100): 3.1 -> 3.2Hurt
Use language embeddings of MLLM part names, not hard correspondencesUniMatch · chair category (in-the-wild)qualitative matchingHurt

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