AI Paper Atlas

Research map / 3D vision / Face and shape

Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency

Fang Zhao, Shengcai Liao, Kaihao Zhang, Ling Shao

NeurIPS 2020 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 13 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 semantic part map as input (ablation)Ours · Market-1501SSIM: 0.310 -> 0.318Improved
add SMPL pose parameters to decoder (ablation)Ours · Market-1501SSIM: 0.315 -> 0.318Improved
add cross-view consistency learning (ablation)Ours · Market-1501SSIM: 0.305 -> 0.318Improved
add cross-view consistency learning (ablation)Ours · Market-1501mask-SSIM: 0.863 -> 0.877Improved
add total variation regularization (ablation)Ours · Market-1501SSIM: 0.316 -> 0.318Improved
add total variation regularization (ablation)Ours · Market-1501mask-SSIM: 0.875 -> 0.877Improved
use human parsing input, cross-view learning and pose vs CMR baselineCMR · Market-1501SSIM: 0.276 -> 0.318Improved
same, on DeepFashionCMR · DeepFashionSSIM: 0.709 -> 0.735Improved
predict texture flow instead of RSTG direct pixel predictionRSTG · Market-1501SSIM: 0.164 -> 0.318Improved

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