Representing a Partially Observed Non-Rigid 3D Human Using Eigen-Texture and Eigen-Deformation

Ryosuke Kimura, Akihiko Sayo, Fabian Lorenzo Dayrit, Yuta Nakashima, Hiroshi Kawasaki, Ambrosio Blanco, Katsushi Ikeuchi

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

2 被引用数 (Scopus)

抄録

Reconstruction of the shape and motion of humans from RGB-D is a challenging problem, receiving much attention in recent years. Recent approaches for full-body reconstruction use a statistic shape model, which is built upon accurate full-body scans of people in skin-tight clothes, to complete invisible parts due to occlusion. Such a statistic model may still be fit to an RGB-D measurement with loose clothes but cannot describe its deformations, such as clothing wrinkles. Observed surfaces may be reconstructed precisely from actual measurements, while we have no cues for unobserved surfaces. For full-body reconstruction with loose clothes, we propose to use lower dimensional embeddings of texture and deformation referred to as eigen-texturing and eigen-deformation, to reproduce views of even unobserved surfaces. Provided a full-body reconstruction from a sequence of partial measurements as 3D meshes, the texture and deformation of each triangle are then embedded using eigen-decomposition. Combined with neural-network-based coefficient regression, our method synthesizes the texture and deformation from arbitrary viewpoints. We evaluate our method using simulated data and visually demonstrate how our method works on real data.

本文言語英語
ホスト出版物のタイトル2018 24th International Conference on Pattern Recognition, ICPR 2018
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1043-1048
ページ数6
ISBN(電子版)9781538637883
DOI
出版ステータス出版済み - 11 26 2018
イベント24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, 中国
継続期間: 8 20 20188 24 2018

出版物シリーズ

名前Proceedings - International Conference on Pattern Recognition
2018-August
ISSN(印刷版)1051-4651

その他

その他24th International Conference on Pattern Recognition, ICPR 2018
Country中国
CityBeijing
Period8/20/188/24/18

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

フィンガープリント 「Representing a Partially Observed Non-Rigid 3D Human Using Eigen-Texture and Eigen-Deformation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル