Perceiving Systems, Computer Vision

CAPE: Dressing SMPL

2020-06-17


CAPE provides a "dressed SMPL" body model. We train CAPE as a conditional Mesh-VAE-GAN to learn the clothing deformation from the SMPL body model, making clothing an additional term on SMPL. CAPE is conditioned on both pose and clothing type, giving the ability to draw samples of clothing to dress different body shapes in a variety of styles and poses.

CAPE provides a "dressed SMPL" body model. We train CAPE as a conditional Mesh-VAE-GAN to learn the clothing deformation from the SMPL body model, making clothing an additional term on SMPL. CAPE is conditioned on both pose and clothing type, giving the ability to draw samples of clothing to dress different body shapes in a variety of styles and poses. Data and code included.

Author(s): Ma, Q., Yang, J., Ranjan, A., Pujades, S., Pons-Moll, G., Tang, S., Black, M. J.
Department(s): Perceiving Systems
Publication(s): Learning to Dress {3D} People in Generative Clothing
Authors: Ma, Q., Yang, J., Ranjan, A., Pujades, S., Pons-Moll, G., Tang, S., Black, M. J.
Release Date: 2020-06-17
Repository: https://github.com/QianliM/CAPE
External Link: https://cape.is.tue.mpg.de/