Nonlocal matting

Philip Lee; Ying Wu

doi:10.1109/CVPR.2011.5995665

Nonlocal matting

Philip Lee^*, Ying Wu

^*Corresponding author for this work

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

148 Scopus citations

Abstract

This work attempts to considerably reduce the amount of user effort in the natural image matting problem. The key observation is that the nonlocal principle, introduced to denoise images, can be successfully applied to the alpha matte to obtain sparsity in matte representation, and therefore dramatically reduce the number of pixels a user needs to manually label. We show how to avoid making the user provide redundant and unnecessary input, develop a method for clustering the image pixels for the user to label, and a method to perform high-quality matte extraction. We show that this algorithm is therefore faster, easier, and higher quality than state of the art methods.

Original language	English (US)
Title of host publication	2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
Pages	2193-2200
Number of pages	8
DOIs	https://doi.org/10.1109/CVPR.2011.5995665
State	Published - Sep 22 2011
Event	2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011 - Colorado Springs, CO, United States Duration: Jun 20 2011 → Jun 25 2011

Other

Other	2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
Country/Territory	United States
City	Colorado Springs, CO
Period	6/20/11 → 6/25/11

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2011.5995665

Cite this

@inproceedings{28c5a29623ff42e0bd716d70946adfb0,

title = "Nonlocal matting",

abstract = "This work attempts to considerably reduce the amount of user effort in the natural image matting problem. The key observation is that the nonlocal principle, introduced to denoise images, can be successfully applied to the alpha matte to obtain sparsity in matte representation, and therefore dramatically reduce the number of pixels a user needs to manually label. We show how to avoid making the user provide redundant and unnecessary input, develop a method for clustering the image pixels for the user to label, and a method to perform high-quality matte extraction. We show that this algorithm is therefore faster, easier, and higher quality than state of the art methods.",

author = "Philip Lee and Ying Wu",

year = "2011",

month = sep,

day = "22",

doi = "10.1109/CVPR.2011.5995665",

language = "English (US)",

isbn = "9781457703942",

pages = "2193--2200",

booktitle = "2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011",

note = "2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011 ; Conference date: 20-06-2011 Through 25-06-2011",

}

TY - GEN

T1 - Nonlocal matting

AU - Lee, Philip

AU - Wu, Ying

PY - 2011/9/22

Y1 - 2011/9/22

N2 - This work attempts to considerably reduce the amount of user effort in the natural image matting problem. The key observation is that the nonlocal principle, introduced to denoise images, can be successfully applied to the alpha matte to obtain sparsity in matte representation, and therefore dramatically reduce the number of pixels a user needs to manually label. We show how to avoid making the user provide redundant and unnecessary input, develop a method for clustering the image pixels for the user to label, and a method to perform high-quality matte extraction. We show that this algorithm is therefore faster, easier, and higher quality than state of the art methods.

AB - This work attempts to considerably reduce the amount of user effort in the natural image matting problem. The key observation is that the nonlocal principle, introduced to denoise images, can be successfully applied to the alpha matte to obtain sparsity in matte representation, and therefore dramatically reduce the number of pixels a user needs to manually label. We show how to avoid making the user provide redundant and unnecessary input, develop a method for clustering the image pixels for the user to label, and a method to perform high-quality matte extraction. We show that this algorithm is therefore faster, easier, and higher quality than state of the art methods.

UR - http://www.scopus.com/inward/record.url?scp=80052888536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052888536&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2011.5995665

DO - 10.1109/CVPR.2011.5995665

M3 - Conference contribution

AN - SCOPUS:80052888536

SN - 9781457703942

SP - 2193

EP - 2200

BT - 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011

T2 - 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011

Y2 - 20 June 2011 through 25 June 2011

ER -

Nonlocal matting

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this