CVPR2024

Garment Recovery with Shape and Deformation Priors

Ren Li, Corentin Dumery, Benoît Guillard, Pascal Fua

Abstract

Trained on Synthetic Data Garment Recovery Figure 1 . We propose a fitting method that leverages shape and deformation priors trained on synthetic data to recover realistic 3D garment mesh from in-the-wild images. We produce triangulated meshes that are directly usable for animation and simulation.