PatchCut: Data-driven object segmentation via local shape transfer

Jimei Yang, Brian Price, Scott Cohen, Zhe Lin, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

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 languageEnglish
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PublisherIEEE Computer Society
Pages1770-1778
Number of pages9
ISBN (Electronic)9781467369640
DOIs
Publication statusPublished - 2015 Oct 14
EventIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States
Duration: 2015 Jun 72015 Jun 12

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume07-12-June-2015
ISSN (Print)1063-6919

Other

OtherIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
CountryUnited States
CityBoston
Period15/6/715/6/12

Fingerprint

Masks
Color
Image understanding
Cascades (fluid mechanics)

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Yang, J., Price, B., Cohen, S., Lin, Z., & Yang, M. H. (2015). PatchCut: Data-driven object segmentation via local shape transfer. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 1770-1778). [7298786] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7298786
Yang, Jimei ; Price, Brian ; Cohen, Scott ; Lin, Zhe ; Yang, Ming Hsuan. / PatchCut : Data-driven object segmentation via local shape transfer. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. pp. 1770-1778 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{55c868e7effc4b0e95fed8822c0963a1,
title = "PatchCut: Data-driven object segmentation via local shape transfer",
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.",
author = "Jimei Yang and Brian Price and Scott Cohen and Zhe Lin and Yang, {Ming Hsuan}",
year = "2015",
month = "10",
day = "14",
doi = "10.1109/CVPR.2015.7298786",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "1770--1778",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",
address = "United States",

}

Yang, J, Price, B, Cohen, S, Lin, Z & Yang, MH 2015, PatchCut: Data-driven object segmentation via local shape transfer. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7298786, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 1770-1778, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 15/6/7. https://doi.org/10.1109/CVPR.2015.7298786

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 proceedingConference 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 -

Yang J, Price B, Cohen S, Lin Z, Yang MH. PatchCut: Data-driven object segmentation via local shape transfer. In 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). https://doi.org/10.1109/CVPR.2015.7298786