AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching

Dongliang Cao, Florian Bernard

CVPR 2023 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 29 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 mesh-to-point-cloud alignment loss Ealign (ablation)Multimodal shape matching · FAUST, SCAPE, and SHREC’19 point cloudsmean geodesic error (×100): 22.7 -> 2.4; 20.9 -> 4.1; 30.8 -> 4.5Improved
Add mesh-point contrastive loss Ence (ablation)Multimodal shape matching · FAUST, SCAPE, and SHREC’19 meshesmean geodesic error (×100): 2.3 -> 2.0; 4.8 -> 3.1; 4.3 -> 4.0Improved
Add mesh-point contrastive loss Ence (ablation)Multimodal shape matching · FAUST, SCAPE, and SHREC’19 point cloudsmean geodesic error (×100): 5.2 -> 2.4; 9.3 -> 4.1; 11.2 -> 4.5Mixed
Remove Ence while retaining Ealign (ablation)Multimodal shape matching · FAUST, SCAPE, and SHREC’19 point cloudsmean geodesic error (×100): 2.4 -> 2.7; 4.1 -> 5.6; 4.5 -> 5.1Hurt
Use multimodal training with mesh functional-map regularization and point-cloud feature matchingOurs · FAUST, SCAPE, and SHREC’19 point cloudsmean geodesic error (×100): 6.0 -> 2.4; 7.8 -> 4.1; 11.7 -> 4.5Improved
Train on SURREAL and evaluate on another datasetOurs · FAUST, SCAPE, and SHREC’19 cross-dataset point cloudsmean geodesic error (×100): 12.2 -> 3.5; 14.1 -> 3.8; 15.9 -> 6.6Improved
Use the proposed self-supervised method rather than DPFM unsupervisedSHREC’16 partial shape matching · CUTS and HOLES point cloudsmean geodesic error (×100): 9.0 -> 7.6; 20.5 -> 15.9Improved
Use the proposed method rather than supervised DPFMSURREAL-PV partial-view matching · SURREAL-PV testmean geodesic error (×100): 7.8 -> 6.3Improved

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