AI Paper Atlas

Research map / 3D vision / Face and shape

Self-supervised 3D Representation Learning of Dressed Humans from Social Media Videos

Yasamin Jafarian, Hyun Soo Park

TPAMI 2022 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 12 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 joint surface-normal loss L_s to depth loss (ablation)L_z model · Tang et al. dataset (ablation, tested without adaptation)depth error (cm): 5.66 -> 5.11Improved
add joint surface-normal loss L_s to depth loss (ablation)L_z model · Tang et al. dataset (ablation, tested without adaptation)normal error (deg): 34.24 -> 29.99Improved
add self-supervised warping loss L_w with TikTok videos (ablation)L_z + L_s · Tang et al. dataset (ablation, tested without adaptation)depth error (cm): 5.11 -> 4.89Improved
add self-supervised warping loss L_w with TikTok videos (ablation)L_z + L_s · Tang et al. dataset (ablation, tested without adaptation)normal error (deg): 29.99 -> 29.36Improved
add self-supervised warping loss L_w with TikTok videos (ablation)L_z + L_s · Tang et al. dataset (ablation, tested without adaptation)reconstruction error (cm): 4.66 -> 4.46Improved
use affine instead of rigid transformation warpingOurs · Vlasic et al. datasetdepth error (dataset scale): 16.9 -> 16.8No clear effect
use affine instead of rigid transformation warpingOurs · Tang et al. datasetdepth error (cm): 5.0 -> 4.8Improved
add photometric consistency loss L_pOurs (affine) · RenderPeople datasetdepth error (cm): 3.2 -> 2.9Improved
add photometric consistency loss L_pOurs (affine) · Tang et al. datasetdepth error (cm): 4.8 -> 5.1Hurt
add photometric consistency loss L_pOurs (affine) · Vlasic et al. datasetdepth error (dataset scale): 16.8 -> 15.9Improved

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