MISC

2019年

SiCloPe: Silhouette-Based Clothed People

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
  • Ryota Natsume
  • ,
  • Shunsuke Saito
  • ,
  • Zeng Huang
  • ,
  • Weikai Chen
  • ,
  • Chongyang Ma
  • ,
  • Hao Li
  • ,
  • Shigeo Morishima

2019-June
開始ページ
4475
終了ページ
4485
記述言語
英語
掲載種別
DOI
10.1109/CVPR.2019.00461
出版者・発行元
IEEE COMPUTER SOC

We introduce a new silhouette-based representation for modeling clothed human bodies using deep generative models. Our method can reconstruct a complete and textured 3D model of a person wearing clothes from a single input picture. Inspired by the visual hull algorithm, our implicit representation uses 2D silhouettes and 3D joints of a body pose to describe the immense shape complexity and variations of clothed people. Given a segmented 2D silhouette of a person and its inferred 3D joints from the input picture, we first synthesize consistent silhouettes from novel view points around the subject. The synthesized silhouettes which are the most consistent with the input segmentation are fed into a deep visual hull algorithm for robust 3D shape prediction. We then infer the texture of the subject's back view using the frontal image and segmentation mask as input to a conditional generative adversarial network. Our experiments demonstrate that our silhouette-based model is an effective representation and the appearance of the back view can be predicted reliably using an image-to-image translation network. While classic methods based on parametric models often fail for single-view images of subjects with challenging clothing, our approach can still produce successful results, which are comparable to those obtained from multi-view input.

リンク情報
DOI
https://doi.org/10.1109/CVPR.2019.00461
DBLP
https://dblp.uni-trier.de/rec/conf/cvpr/NatsumeSH0MLM19
arXiv
http://arxiv.org/abs/arXiv:1901.00049
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000529484004067&DestApp=WOS_CPL
Scopus
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85076996866&origin=inward
Scopus Citedby
https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85076996866&origin=inward
URL
http://arxiv.org/abs/1901.00049v2
URL
http://arxiv.org/pdf/1901.00049v2 本文へのリンクあり
ID情報
  • DOI : 10.1109/CVPR.2019.00461
  • ISSN : 1063-6919
  • DBLP ID : conf/cvpr/NatsumeSH0MLM19
  • arXiv ID : arXiv:1901.00049
  • SCOPUS ID : 85076996866
  • Web of Science ID : WOS:000529484004067

エクスポート
BibTeX RIS