BodyNet: Volumetric Inference of 3D Human Body Shapes

Gül Varol 1, 2 Duygu Ceylan 3 Bryan Russell 3 Jimei Yang 3 Ersin Yumer 3 Ivan Laptev 1 Cordelia Schmid 2
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria de Paris
2 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : Human shape estimation is an important task for video editing , animation and fashion industry. Predicting 3D human body shape from natural images, however, is highly challenging due to factors such as variation in human bodies, clothing and viewpoint. Prior methods addressing this problem typically attempt to fit parametric body models with certain priors on pose and shape. In this work we argue for an alternative representation and propose BodyNet, a neural network for direct inference of volumetric body shape from a single image. BodyNet is an end-to-end trainable network that benefits from (i) a volumetric 3D loss, (ii) a multi-view re-projection loss, and (iii) intermediate supervision of 2D pose, 2D body part segmentation, and 3D pose. Each of them results in performance improvement as demonstrated by our experiments. To evaluate the method, we fit the SMPL model to our network output and show state-of-the-art results on the SURREAL and Unite the People datasets, outperforming recent approaches. Besides achieving state-of-the-art performance, our method also enables volumetric body-part segmentation.
Type de document :
Communication dans un congrès
European Conference on Computer Vision 2018, Sep 2018, Munich, Germany
Liste complète des métadonnées

https://hal.inria.fr/hal-01852169
Contributeur : Gul Varol <>
Soumis le : mercredi 1 août 2018 - 01:17:09
Dernière modification le : dimanche 5 août 2018 - 21:58:43

Fichier

VarolECCV2018.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01852169, version 1
  • ARXIV : 1804.04875

Collections

Citation

Gül Varol, Duygu Ceylan, Bryan Russell, Jimei Yang, Ersin Yumer, et al.. BodyNet: Volumetric Inference of 3D Human Body Shapes. European Conference on Computer Vision 2018, Sep 2018, Munich, Germany. 〈hal-01852169〉

Partager

Métriques

Consultations de la notice

156

Téléchargements de fichiers

49