AI Paper Atlas

Research map / 3D vision / Face and shape

High-Fidelity Modeling of Generalizable Wrinkle Deformation

Jingfan Guo, Jae Shin Yoon, Shunsuke Saito, Takaaki Shiratori, Hyun Soo Park

ECCV 2024 · 3D vision › Face and shape · approach: Clothed human modeling · 0 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
condition wrinkle diffusion on norm of Green-Lagrange strain instead of surface normal (ablation)strain-conditioned wrinkle diffusion · T-shirt OOD testFID: 129.19 -> 75.05Improved
condition on strain norm instead of full strain tensor (ablation)strain-conditioned wrinkle diffusion · Skirt OOD testFID: 116.05 -> 45.09Improved
use strain-conditioned diffusion with 3D displacement instead of LFGD displacement in global framewrinkle generation · T-shirt in-distributionEv (10^-2 m): 0.586 -> 0.347Improved
use wrinkle generation on the base mesh versus no wrinklesclothing mesh · T-shirt OOD testFID: 212.08 -> 75.05Improved
apply DDE normal-map enhancement to a smooth base meshDDE · T-shirt in-distributionEv (10^-2 m): 1.507 vs 0.835 (DeepWrinkles)Hurt
apply LFGD wrinkles on the base meshLFGD · T-shirt OOD testFID: 212.08 -> 305.89Hurt

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