PatchCut: Data-Driven Object Segmentation via Local Shape Transfer

Jimei Yang, Brian Price, Scott Cohen, Zhe Lin, Ming-Hsuan Yang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1770-1778

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Yang_2015_CVPR,
author = {Yang, Jimei and Price, Brian and Cohen, Scott and Lin, Zhe and Yang, Ming-Hsuan},
title = {PatchCut: Data-Driven Object Segmentation via Local Shape Transfer},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}