Learning to Dress 3D People in Generative Clothing - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Learning to Dress 3D People in Generative Clothing

Résumé

Three-dimensional human body models are widely usedin the analysis of human pose and motion. Existing models, however, are learned from minimally-clothed 3D scansand thus do not generalize to the complexity of dressed people in common images and videos. Additionally, current models lack the expressive power needed to represent the complex non-linear geometry of pose-dependent clothing shapes. To address this, we learn a generative 3D meshmodel of clothed people from 3D scans with varying poseand clothing. Specifically, we train a conditional Mesh-VAE-GAN to learn the clothing deformation from the SMPL body model, making clothing an additional term in SMPL. Our model 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. To preserve wrinkle detail, our Mesh-VAE-GAN extends patchwise discriminators to 3D meshes. Our model, named CAPE, represents global shape and fine local structure, effectively extending the SMPL body model to clothing. To our knowledge, this is the first generative model that directly dresses 3D human body meshes and generalizes to different poses.The model, code and data are available for research pur-poses at https://cape.is.tue.mpg.de
Fichier principal
Vignette du fichier
CAPE_paper.pdf (4.37 Mo) Télécharger le fichier
Vignette du fichier
CAPE_teaser_PS_website_v3.png (628.72 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Loading...

Dates et versions

hal-02988291 , version 1 (04-11-2020)

Identifiants

Citer

Qianli Ma, Jinlong Yang, Anurag Ranjan, Sergi Pujades, Gerard Pons-Moll, et al.. Learning to Dress 3D People in Generative Clothing. CVPR 2020 - IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2020, Seattle, United States. pp.6468-6477, ⟨10.1109/CVPR42600.2020.00650⟩. ⟨hal-02988291⟩
216 Consultations
306 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More