AI Paper Atlas

Research map / 3D vision / Human pose estimation

Human Motion Transfer With 3D Constraints and Detail Enhancement

Yang-Tian Sun, Qiancheng Fu, Yue-Ren Jiang, Zitao Liu, Yu‐Kun Lai, Hongbo Fu, Lin Gao

TPAMI 2022 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 24 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 3D projection condition to 2D pose condition (MT(2D+3D)) (ablation)MT-Net · Dance dataset, cross-subject transferFID: 58.62 -> 55.77Improved
add 3D projection condition to 2D pose condition (MT(2D+3D)) (ablation)MT-Net · Dance dataset, self-transferSSIM: 0.828 -> 0.856Improved
use 3D condition alone instead of 2D condition (ablation)MT-Net · Dance dataset, cross-subject transferIS-ReID: 3.523 -> 3.632Improved
add DE-Net detail enhancement to MT(2D+3D) (ablation)full pipeline · Dance dataset, self-transferSSIM: 0.856 -> 0.891Improved
add DE-Net to MT(2D) (ablation)MT-Net · Dance dataset, self-transferLPIPS: 0.064 -> 0.043Improved
add DE-Net to MT(2D) (ablation)MT-Net · Dance dataset, cross-subject transferIS-ReID: 3.523 -> 3.587Improved
use learned blending parameter instead of average blending (ablation)DE-Net · Dance dataset, cross-subject transferFID: 53.76 -> 51.26Improved
use learned blending parameter instead of average blending (ablation)DE-Net · Dance dataset, self-transferSSIM: 0.887 -> 0.891Improved
use Laplacian-projection 3D pose labels instead of UV-coordinate pose labels of prior work (ablation)pose GAN condition · Dance dataset, cross-subject transferFID: 58.42 -> 51.26Improved
use Laplacian-projection 3D pose labels instead of prior pose labels (ablation)pose GAN condition · Dance dataset, cross-subject transferIS-ReID: 3.612 -> 4.015Improved
add 3D condition to MT(2D)+DE (self-transfer, same body shape) (ablation)full pipeline · Dance dataset, self-transferSSIM: 0.877 -> 0.891No clear effect
compare to vid2vid, Chan et al. and Liquid Warping GANOurs · Dance dataset, cross-subject transferFID: 57.02 -> 51.26Improved

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