FuzzyMatte: A computationally efficient scheme for interactive matting

Yuanjie Zheng; Chandra Kambhamettu; Jingyi Yu; Thomas Bauer; Karl Steiner

doi:10.1109/CVPR.2008.4587455

FuzzyMatte: A computationally efficient scheme for interactive matting

Yuanjie Zheng, Chandra Kambhamettu, Jingyi Yu, Thomas Bauer, Karl Steiner

School of Medicine

Hackensack Meridian School of Medicine

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

Abstract

In this paper, we propose an online interactive matting algorithm, which we call FuzzyMatte. Our framework is based on computing the fuzzy connectedness (FC) [20] from each unknown pixel to the known foreground and background. FC effectively captures the adjacency and similarity between image elements and can be efficiently computed using the strongest connected path searching algorithm. The final alpha value at each pixel can then be calculated from its FC. While many previous methods need to completely recompute the matte when new inputs are provided, FuzzyMatte effectively integrates these new inputs with the previously estimated matte by efficiently recomputing the FC value for a small subset of pixels. Thus, the computational overhead between each iteration of the refinement is significantly reduced. We demonstrate FuzzyMatte on a wide range of images. We show that FuzzyMatte updates the matte in an online interactive setting and generates high quality matte for complex images.

Original language	English
Title of host publication	26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
DOIs	https://doi.org/10.1109/CVPR.2008.4587455
State	Published - 2008
Event	26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR - Anchorage, AK, United States Duration: Jun 23 2008 → Jun 28 2008

Publication series

Name	26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

Conference

Conference	26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
Country/Territory	United States
City	Anchorage, AK
Period	6/23/08 → 6/28/08

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Control and Systems Engineering

Access to Document

10.1109/CVPR.2008.4587455

Cite this

@inproceedings{30a3c8952a2a4919855be1d05ef30ea5,

title = "FuzzyMatte: A computationally efficient scheme for interactive matting",

abstract = "In this paper, we propose an online interactive matting algorithm, which we call FuzzyMatte. Our framework is based on computing the fuzzy connectedness (FC) [20] from each unknown pixel to the known foreground and background. FC effectively captures the adjacency and similarity between image elements and can be efficiently computed using the strongest connected path searching algorithm. The final alpha value at each pixel can then be calculated from its FC. While many previous methods need to completely recompute the matte when new inputs are provided, FuzzyMatte effectively integrates these new inputs with the previously estimated matte by efficiently recomputing the FC value for a small subset of pixels. Thus, the computational overhead between each iteration of the refinement is significantly reduced. We demonstrate FuzzyMatte on a wide range of images. We show that FuzzyMatte updates the matte in an online interactive setting and generates high quality matte for complex images.",

author = "Yuanjie Zheng and Chandra Kambhamettu and Jingyi Yu and Thomas Bauer and Karl Steiner",

year = "2008",

doi = "10.1109/CVPR.2008.4587455",

language = "English",

isbn = "9781424422432",

series = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR",

booktitle = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR",

note = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR ; Conference date: 23-06-2008 Through 28-06-2008",

}

Zheng, Y, Kambhamettu, C, Yu, J, Bauer, T & Steiner, K 2008, FuzzyMatte: A computationally efficient scheme for interactive matting. in 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR., 4587455, 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Anchorage, AK, United States, 6/23/08. https://doi.org/10.1109/CVPR.2008.4587455

FuzzyMatte: A computationally efficient scheme for interactive matting. / Zheng, Yuanjie; Kambhamettu, Chandra; Yu, Jingyi et al.
26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2008. 4587455 (26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR).

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

TY - GEN

T1 - FuzzyMatte

T2 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

AU - Zheng, Yuanjie

AU - Kambhamettu, Chandra

AU - Yu, Jingyi

AU - Bauer, Thomas

AU - Steiner, Karl

PY - 2008

Y1 - 2008

N2 - In this paper, we propose an online interactive matting algorithm, which we call FuzzyMatte. Our framework is based on computing the fuzzy connectedness (FC) [20] from each unknown pixel to the known foreground and background. FC effectively captures the adjacency and similarity between image elements and can be efficiently computed using the strongest connected path searching algorithm. The final alpha value at each pixel can then be calculated from its FC. While many previous methods need to completely recompute the matte when new inputs are provided, FuzzyMatte effectively integrates these new inputs with the previously estimated matte by efficiently recomputing the FC value for a small subset of pixels. Thus, the computational overhead between each iteration of the refinement is significantly reduced. We demonstrate FuzzyMatte on a wide range of images. We show that FuzzyMatte updates the matte in an online interactive setting and generates high quality matte for complex images.

AB - In this paper, we propose an online interactive matting algorithm, which we call FuzzyMatte. Our framework is based on computing the fuzzy connectedness (FC) [20] from each unknown pixel to the known foreground and background. FC effectively captures the adjacency and similarity between image elements and can be efficiently computed using the strongest connected path searching algorithm. The final alpha value at each pixel can then be calculated from its FC. While many previous methods need to completely recompute the matte when new inputs are provided, FuzzyMatte effectively integrates these new inputs with the previously estimated matte by efficiently recomputing the FC value for a small subset of pixels. Thus, the computational overhead between each iteration of the refinement is significantly reduced. We demonstrate FuzzyMatte on a wide range of images. We show that FuzzyMatte updates the matte in an online interactive setting and generates high quality matte for complex images.

UR - http://www.scopus.com/inward/record.url?scp=51949096579&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2008.4587455

DO - 10.1109/CVPR.2008.4587455

M3 - Conference contribution

SN - 9781424422432

T3 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

BT - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

Y2 - 23 June 2008 through 28 June 2008

ER -

FuzzyMatte: A computationally efficient scheme for interactive matting

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this