AI Paper Atlas

Research map / 3D vision / Face and shape

Learning to Transfer Texture From Clothing Images to 3D Humans

Aymen Mir, Thiemo Alldieck, Gerard Pons-Moll

CVPR 2020 · 3D vision › Face and shape · approach: Clothed human modeling · 127 citations (OpenAlex)

Check 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
Use Pix2Surf texture transfer instead of the tested baseline texturing methods3D garment texturing · User study (20 videos)participant preference: 100%Improved
Predict pixel-to-UV correspondences from silhouette coordinate masks rather than generating texture maps directlyPix2Surf · Clothing-image texture transfertexture detail and mapping qualityImproved
Use Pix2Surf instead of shape-context matching with thin-plate-spline warping3D garment texturing · Clothing-image texture transfertexture mapping qualityImproved
Increase the adversarial-loss weight (ablation)Pix2Pix baseline · Clothing-image texture transferperformanceHurt
Use Pix2Surf's 3D texture transfer rather than image-based virtual try-on for extreme posesVirtual try-on · Extreme posesgeneralization to poseImproved

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