filename     : Dib17b.pdf
entry        : inproceedings
conference   : Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, July 21-26, 2017
pages        : 
year         : 2017
month        : July
title        : Human Shape from Silhouettes using Generative HKS Descriptors and Cross-Modal Neural Networks
subtitle     :
author       : Endri Dibra and Himanshu Jain and Cengiz {\"{O}}ztireli and Remo Ziegler and Markus Gross
booktitle    : Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
ISSN/ISBN    :
editor       : 
publisher    : 
publ.place   : 
volume       : 
issue        : 
language     : english
keywords     : human shape estimation, deep networks, shape from silhouettes, CNNs, multi-view learning, cross-modal neural networks
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 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.