Repository logo
 

Human Shape from Silhouettes Using Generative HKS Descriptors and Cross-Modal Neural Networks

Accepted version
Peer-reviewed

Type

Conference Object

Change log

Authors

Dibra, Endri 
Jain, Himanshu 
Oztireli, Cengiz 
Ziegler, Remo 
Gross, Markus 

Abstract

In this work, we present a novel method for capturing human body shape from a single scaled silhouette. We combine deep correlated features capturing different 2D views, and embedding spaces based on 3D cues in a novel convolutional neural network (CNN) based architecture. We first train a CNN to find a richer body shape representation space from pose invariant 3D human shape descriptors. Then, we learn a mapping from silhouettes to this representation space, with the help of a novel architecture that exploits the correlation of multi-view data during training time, to improve prediction at test time. We extensively validate our results on synthetic and real data, demonstrating significant improvements in accuracy as compared to the state-of-the-art, and providing a practical system for detailed human body measurements from a single image.

Description

Keywords

46 Information and Computing Sciences, 4607 Graphics, Augmented Reality and Games, 4611 Machine Learning, Bioengineering, 1.1 Normal biological development and functioning, Generic health relevance

Journal Title

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Conference Name

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Journal ISSN

Volume Title

Publisher

IEEE

Rights

All rights reserved