• DOI:10.1109/CVPR.2019.00461
Corpus ID: 57373829

SiCloPe: Silhouette-Based Clothed People

@article{Natsume2019SiCloPeSC,
  title={SiCloPe: Silhouette-Based Clothed People},
  author={R. Natsume and S. Saito and Zeng Huang and Weikai Chen and Chongyang Ma and H. Li and S. Morishima},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={4475-4485}
}

R. Natsume, S. Saito, +4 authors S. Morishima

Published 2019

Computer Science

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

We introduce a new silhouette-based representation for modeling clothed human bodies using deep generative models. [...] Key Method 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.Expand Abstract

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed