Can I read Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration on EtoBox?

Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration by Guo, Jingfan; Prada, Fabian; Xiang, Donglai; Romero, Javier; Wu, Chenglei; Park, Hyun Soo; Shiratori, Takaaki; Saito, Shunsuke is a scholarly article available to read on EtoBox.

What is Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration about?

Registering clothes from 4D scans with vertex-accurate correspondence is challenging, yet important for dynamic appearance modeling and physics parameter estimation from real-world data. However, previous methods either rely on texture information, which is not always reliable, or achieve only coarse-level alignment. In this work, we present a novel approach to enabling accurate surface registration of texture-less clothes with large deformation. Our key idea is to effectively leverage a shape prior learned from pre-captured clothing using diffusion models. We also propose a multi-stage guidance scheme based on learned functional maps, which stabilizes registration for large-scale deformation even when they vary significantly from training data. Using high-fidelity real captured clothes, our experiments show that the proposed approach based on diffusion models generalizes better than surface registration with VAE or PCA-based priors, outperforming both optimization-based and learning-based non-rigid registration methods for both interpolation and extrapolation tests.

Author

Guo, Jingfan; Prada, Fabian; Xiang, Donglai; Romero, Javier; Wu, Chenglei; Park, Hyun Soo; Shiratori, Takaaki; Saito, Shunsuke

Published

2023

Language

EN