Abstract
Object segmentation is highly desirable for image understanding and editing. Current interactive tools require a great deal of user effort while automatic methods are usually limited to images of special object categories or with high color contrast. In this paper, we propose a data-driven algorithm that uses examples to break through these limits. As similar objects tend to share similar local shapes, we match query image patches with example images in multiscale to enable local shape transfer. The transferred local shape masks constitute a patch-level segmentation solution space and we thus develop a novel cascade algorithm, PatchCut, for coarse-to-fine object segmentation. In each stage of the cascade, local shape mask candidates are selected to refine the estimated segmentation of the previous stage iteratively with color models. Experimental results on various datasets (Weizmann Horse, Fashionista, Object Discovery and PASCAL) demonstrate the effectiveness and robustness of our algorithm.
| Original language | English |
|---|---|
| Title of host publication | IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 |
| Publisher | IEEE Computer Society |
| Pages | 1770-1778 |
| Number of pages | 9 |
| ISBN (Electronic) | 9781467369640 |
| DOIs | |
| Publication status | Published - 2015 Oct 14 |
| Event | IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States Duration: 2015 Jun 7 → 2015 Jun 12 |
Publication series
| Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|---|
| Volume | 07-12-June-2015 |
| ISSN (Print) | 1063-6919 |
Other
| Other | IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 |
|---|---|
| Country | United States |
| City | Boston |
| Period | 15/6/7 → 15/6/12 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition
Cite this
}
PatchCut : Data-driven object segmentation via local shape transfer. / Yang, Jimei; Price, Brian; Cohen, Scott; Lin, Zhe; Yang, Ming Hsuan.
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 1770-1778 7298786 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - PatchCut
T2 - Data-driven object segmentation via local shape transfer
AU - Yang, Jimei
AU - Price, Brian
AU - Cohen, Scott
AU - Lin, Zhe
AU - Yang, Ming Hsuan
PY - 2015/10/14
Y1 - 2015/10/14
N2 - Object segmentation is highly desirable for image understanding and editing. Current interactive tools require a great deal of user effort while automatic methods are usually limited to images of special object categories or with high color contrast. In this paper, we propose a data-driven algorithm that uses examples to break through these limits. As similar objects tend to share similar local shapes, we match query image patches with example images in multiscale to enable local shape transfer. The transferred local shape masks constitute a patch-level segmentation solution space and we thus develop a novel cascade algorithm, PatchCut, for coarse-to-fine object segmentation. In each stage of the cascade, local shape mask candidates are selected to refine the estimated segmentation of the previous stage iteratively with color models. Experimental results on various datasets (Weizmann Horse, Fashionista, Object Discovery and PASCAL) demonstrate the effectiveness and robustness of our algorithm.
AB - Object segmentation is highly desirable for image understanding and editing. Current interactive tools require a great deal of user effort while automatic methods are usually limited to images of special object categories or with high color contrast. In this paper, we propose a data-driven algorithm that uses examples to break through these limits. As similar objects tend to share similar local shapes, we match query image patches with example images in multiscale to enable local shape transfer. The transferred local shape masks constitute a patch-level segmentation solution space and we thus develop a novel cascade algorithm, PatchCut, for coarse-to-fine object segmentation. In each stage of the cascade, local shape mask candidates are selected to refine the estimated segmentation of the previous stage iteratively with color models. Experimental results on various datasets (Weizmann Horse, Fashionista, Object Discovery and PASCAL) demonstrate the effectiveness and robustness of our algorithm.
UR - http://www.scopus.com/inward/record.url?scp=84959204067&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84959204067&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2015.7298786
DO - 10.1109/CVPR.2015.7298786
M3 - Conference contribution
AN - SCOPUS:84959204067
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1770
EP - 1778
BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PB - IEEE Computer Society
ER -