AI Paper Atlas

Research map / 3D vision / Human pose estimation

Unsupervised 3D Pose Transfer With Cross Consistency and Dual Reconstruction

Chaoyue Song, Jiacheng Wei, Ruibo Li, Fayao Liu, Guosheng Lin

TPAMI 2023 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 25 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 ARAP deformer in the training loop (ablation)X-DualNet · SMPLPMD: 1.98 -> 1.67Improved
add ARAP deformer in the training loop (ablation)X-DualNet · SMPLCD: 3.37 -> 2.71Improved
add backward correspondence loss (ablation)X-DualNet · SMPLPMD: 1.84 -> 1.67Improved
add backward correspondence loss (ablation)X-DualNet · SMPLEMD: 6.35 -> 5.96Improved
use ElaIN instead of SPAdaIN (ablation)3D-CoreNet · SMPLPMD: 1.01 -> 0.49Improved
use ElaIN instead of SPAdaIN (ablation)3D-CoreNet · SMPLEMD: 4.66 -> 3.61Improved
use X-DualNet instead of unsupervised baselineunsupervised baseline · SMALPMD: 16.50 -> 4.48Improved
use X-DualNet instead of unsupervised baselineunsupervised baseline · SMPLCD: 4.05 -> 2.71Improved
unsupervised X-DualNet vs supervised NPTNPT · SMPLPMD: 2.77 -> 1.67Improved
supervised 3D-CoreNet vs unsupervised X-DualNetX-DualNet · SMPLPMD: 1.67 -> 0.49Hurt

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