NON-rigid structure from motion via sparse self-expressive representation

Junjie Hu, Terumasa Aoki

研究成果: Conference contribution

抄録

To simultaneously recover 3D shapes of non-rigid object and camera motions from 2D corresponding points is a difficult task in computer vision. This task is called Non-rigid Structure from motion(NRSfM). To solve this ill-posed problem, many existing methods rely on low rank assumption. However, the value of rank has to be accurately predefined because incorrect value can largely degrade the reconstruction performance. Unfortunately, these is no automatic solution to determine this value. In this paper, we present a self-expressive method that models 3D shapes with a sparse combination of other 3D shapes from the same structure. One of the biggest advantages is that it doesn't need the rank to be predefined. Also, unlike other learning-based methods, our method doesn't need learning step. Experimental results validate the efficiency of our method.

本文言語English
ホスト出版物のタイトル2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
出版社IEEE Computer Society
ページ4537-4541
ページ数5
ISBN(電子版)9781509021758
DOI
出版ステータスPublished - 2018 2 20
イベント24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
継続期間: 2017 9 172017 9 20

出版物シリーズ

名前Proceedings - International Conference on Image Processing, ICIP
2017-September
ISSN(印刷版)1522-4880

Other

Other24th IEEE International Conference on Image Processing, ICIP 2017
国/地域China
CityBeijing
Period17/9/1717/9/20

ASJC Scopus subject areas

  • ソフトウェア
  • コンピュータ ビジョンおよびパターン認識
  • 信号処理

フィンガープリント

「NON-rigid structure from motion via sparse self-expressive representation」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