Based on sample-pair refinement and local optimization, this paper proposes a high-accuracy and quick matting algorithm. First, in order to gather foreground/background samples effectively, we shoot rays in hybrid (gradient and uniform) directions. This strategy utilizes the prior knowledge to adjust the directions for effective searching. Second, we refine sample-pairs of pixels by taking into account neighbors'. Both high confidence sample-pairs and usable foreground/background components are utilized and thus more accurate and smoother matting results are achieved. Third, to reduce the computational cost of sample-pair selection in coarse matting, this paper proposes an adaptive sample clustering approach. Most redundant samples are eliminated adaptively, where the computational cost decreases significantly. Finally, we convert fine matting into a de-noising problem, which is optimized by minimizing the observation and state errors iteratively and locally. This leads to less space and time complexity compared with global optimization. Experiments demonstrate that we outperform other state-of-the-art methods in local matting both on accuracy and efficiency.
Bei HE
Tsinghua University
Guijin WANG
Tsinghua University
Chenbo SHI
Tsinghua University
Xuanwu YIN
Tsinghua University
Bo LIU
Tsinghua University
Xinggang LIN
Tsinghua University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Bei HE, Guijin WANG, Chenbo SHI, Xuanwu YIN, Bo LIU, Xinggang LIN, "High-Accuracy and Quick Matting Based on Sample-Pair Refinement and Local Optimization" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 9, pp. 2096-2106, September 2013, doi: 10.1587/transinf.E96.D.2096.
Abstract: Based on sample-pair refinement and local optimization, this paper proposes a high-accuracy and quick matting algorithm. First, in order to gather foreground/background samples effectively, we shoot rays in hybrid (gradient and uniform) directions. This strategy utilizes the prior knowledge to adjust the directions for effective searching. Second, we refine sample-pairs of pixels by taking into account neighbors'. Both high confidence sample-pairs and usable foreground/background components are utilized and thus more accurate and smoother matting results are achieved. Third, to reduce the computational cost of sample-pair selection in coarse matting, this paper proposes an adaptive sample clustering approach. Most redundant samples are eliminated adaptively, where the computational cost decreases significantly. Finally, we convert fine matting into a de-noising problem, which is optimized by minimizing the observation and state errors iteratively and locally. This leads to less space and time complexity compared with global optimization. Experiments demonstrate that we outperform other state-of-the-art methods in local matting both on accuracy and efficiency.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.2096/_p
Copy
@ARTICLE{e96-d_9_2096,
author={Bei HE, Guijin WANG, Chenbo SHI, Xuanwu YIN, Bo LIU, Xinggang LIN, },
journal={IEICE TRANSACTIONS on Information},
title={High-Accuracy and Quick Matting Based on Sample-Pair Refinement and Local Optimization},
year={2013},
volume={E96-D},
number={9},
pages={2096-2106},
abstract={Based on sample-pair refinement and local optimization, this paper proposes a high-accuracy and quick matting algorithm. First, in order to gather foreground/background samples effectively, we shoot rays in hybrid (gradient and uniform) directions. This strategy utilizes the prior knowledge to adjust the directions for effective searching. Second, we refine sample-pairs of pixels by taking into account neighbors'. Both high confidence sample-pairs and usable foreground/background components are utilized and thus more accurate and smoother matting results are achieved. Third, to reduce the computational cost of sample-pair selection in coarse matting, this paper proposes an adaptive sample clustering approach. Most redundant samples are eliminated adaptively, where the computational cost decreases significantly. Finally, we convert fine matting into a de-noising problem, which is optimized by minimizing the observation and state errors iteratively and locally. This leads to less space and time complexity compared with global optimization. Experiments demonstrate that we outperform other state-of-the-art methods in local matting both on accuracy and efficiency.},
keywords={},
doi={10.1587/transinf.E96.D.2096},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - High-Accuracy and Quick Matting Based on Sample-Pair Refinement and Local Optimization
T2 - IEICE TRANSACTIONS on Information
SP - 2096
EP - 2106
AU - Bei HE
AU - Guijin WANG
AU - Chenbo SHI
AU - Xuanwu YIN
AU - Bo LIU
AU - Xinggang LIN
PY - 2013
DO - 10.1587/transinf.E96.D.2096
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2013
AB - Based on sample-pair refinement and local optimization, this paper proposes a high-accuracy and quick matting algorithm. First, in order to gather foreground/background samples effectively, we shoot rays in hybrid (gradient and uniform) directions. This strategy utilizes the prior knowledge to adjust the directions for effective searching. Second, we refine sample-pairs of pixels by taking into account neighbors'. Both high confidence sample-pairs and usable foreground/background components are utilized and thus more accurate and smoother matting results are achieved. Third, to reduce the computational cost of sample-pair selection in coarse matting, this paper proposes an adaptive sample clustering approach. Most redundant samples are eliminated adaptively, where the computational cost decreases significantly. Finally, we convert fine matting into a de-noising problem, which is optimized by minimizing the observation and state errors iteratively and locally. This leads to less space and time complexity compared with global optimization. Experiments demonstrate that we outperform other state-of-the-art methods in local matting both on accuracy and efficiency.
ER -