AI Paper Atlas

Research map / 3D vision / Human pose estimation

MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learning

Jiaze Sun, Zhixiang Chen, Tae-Kyun Kim

ICCV 2023 · 3D vision › Human pose estimation · approach: Category-level pose estimation · 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 mesh-level and point-level contrastive losses to supervised 3D-CoreNet3D-CoreNet · SMPL (supervised)PMD: 0.36 -> 0.30Improved
add latent disentanglement (separate pose and identity channels) to unsupervised 3D-CoreNet (ablation)3D-CoreNet unsupervised · SMPL (unsupervised)PMD: 14.09 -> 0.76Improved
add mesh and point contrastive losses on top of latent disentanglement (unsupervised) (ablation)3D-CoreNet unsupervised · DFAUST (unsupervised)PMD: 92.45 -> 61.22Improved
add point-level contrastive loss (lambda_p=1) in supervised setting (ablation)MAPConNet · SMPL (supervised)PMD: 0.36 -> 0.35Improved
add mesh-level contrastive loss on SC (lambda_m,s=1) in supervised setting (ablation)MAPConNet · SMPL (supervised)PMD: 0.36 -> 0.31Improved
add both mesh and point losses in supervised setting (ablation)MAPConNet · SMPL (supervised)PMD: 0.36 -> 0.30Improved
add point loss in unsupervised setting (ablation)MAPConNet · SMPL (unsupervised)PMD: 0.76 -> 0.59Improved
add SC mesh loss on top of CC mesh loss (unsupervised) (ablation)MAPConNet · SMPL (unsupervised)PMD: 0.60 -> 0.59No clear effect
add unlabelled meshes to 50% labelled training (semi-supervised)MAPConNet · SMPLPMD: 3.69 -> 0.40Improved
add unlabelled DFAUST to SMPL-supervised trainingMAPConNet · DFAUSTPMD: 120.10 -> 36.23Improved
use mesh loss without point loss (ablation)MAPConNet · SMPL warped outputwarped output shrinkingMixed

Later papers that compared with this method

1 later accepted paper reports MAPConNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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