AI Paper Atlas

Research map / 3D vision / Face and shape

Self-supervised Learning of Implicit Shape Representation with Dense Correspondence for Deformable Objects

Baowen Zhang, Jiahe Li, Xiaoming Deng, Yinda Zhang, Cuixia Ma, Hongan Wang

ICCV 2023 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 4 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 the neighborhood rigid loss L_nbr (ablation)Ours · DeformingThings4D bearChamfer distance: 2.045 -> 0.439Improved
add the self-correspondence loss L_recon (ablation)Ours · DeformingThings4D bearChamfer distance: 358.129 -> 0.439Improved
add the piece-wise rigid loss L_pr (ablation)Ours · DeformingThings4D bearcorrespondence error: 0.0858 -> 0.0700Improved
add the reflection penalty on top of L_arap in local rigid loss (ablation)Ours · DeformingThings4D bearChamfer distance: 0.609 -> 0.439Improved
use proposed local rigid loss instead of elastic loss (ablation)Ours · DeformingThings4D bearChamfer distance: 0.815 -> 0.439Improved
add template normal loss L_pfn (ablation)Ours · DeformingThings4D bearChamfer distance: 0.547 -> 0.439Improved
add SDF value as encoder input (ablation)Ours · D-FAUST subject 50026correspondence error: 0.0265 -> 0.0141Improved
add part prediction network psi_e (ablation)Ours · D-FAUST subject 50026Chamfer distance: 1.174 -> 0.687Improved
increase number of parts from 5 to 20 (ablation)piece-wise rigid constraint · D-FAUSTcorrespondence error: 0.0448 -> 0.0141Improved
neighborhood sigma 0.05 versus 0.1 (ablation)neighborhood rigid constraint · D-FAUSTcorrespondence error: 0.0520 -> 0.0141Improved
embed template in the shape latent space instead of a separate template (ablation)Ours · qualitative template visualizationtemplate qualityImproved
use the proposed method versus 3D-CODEDDeformingThings4D · DeformingThings4D averageChamfer distance: 1.658 -> 1.165Mixed

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