The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
본 논문에서는 다중 선형 모델과 행렬 랭크 최소화를 기반으로 한 이미지 인페인팅 알고리즘을 제안합니다. AR(자동 회귀) 모델을 사용하여 이미지를 모델링할 수 있다는 가정을 기반으로 여러 인페인팅 알고리즘이 이전에 제안되었습니다. 그러나 이러한 알고리즘은 이미지가 고정된 모델 순서를 갖는 위치 불변 선형 모델에 의해 모델링된다고 가정하기 때문에 자연 사진에 적용할 때 제대로 수행되지 않습니다. 인페인팅 품질을 향상시키기 위해 이 연구에서는 다중 AR 모델을 도입하고 희소 정규화를 통한 다중 행렬 순위 최소화를 기반으로 하는 이미지 인페인팅 알고리즘을 제안합니다. 이를 통해 반복적 부분 행렬 축소 알고리즘을 기반으로 실용적인 알고리즘을 제공하고, 제안된 알고리즘의 효율성을 보여주는 수치 예를 제공합니다.
Tomohiro TAKAHASHI
Tokai University
Katsumi KONISHI
Hosei University
Kazunori URUMA
Kougakuin University
Toshihiro FURUKAWA
Tokyo University of Science
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.
부
Tomohiro TAKAHASHI, Katsumi KONISHI, Kazunori URUMA, Toshihiro FURUKAWA, "Multiple Subspace Model and Image-Inpainting Algorithm Based on Multiple Matrix Rank Minimization" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 12, pp. 2682-2692, December 2020, doi: 10.1587/transinf.2020EDP7086.
Abstract: This paper proposes an image inpainting algorithm based on multiple linear models and matrix rank minimization. Several inpainting algorithms have been previously proposed based on the assumption that an image can be modeled using autoregressive (AR) models. However, these algorithms perform poorly when applied to natural photographs because they assume that an image is modeled by a position-invariant linear model with a fixed model order. In order to improve inpainting quality, this work introduces a multiple AR model and proposes an image inpainting algorithm based on multiple matrix rank minimization with sparse regularization. In doing so, a practical algorithm is provided based on the iterative partial matrix shrinkage algorithm, with numerical examples showing the effectiveness of the proposed algorithm.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7086/_p
부
@ARTICLE{e103-d_12_2682,
author={Tomohiro TAKAHASHI, Katsumi KONISHI, Kazunori URUMA, Toshihiro FURUKAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Multiple Subspace Model and Image-Inpainting Algorithm Based on Multiple Matrix Rank Minimization},
year={2020},
volume={E103-D},
number={12},
pages={2682-2692},
abstract={This paper proposes an image inpainting algorithm based on multiple linear models and matrix rank minimization. Several inpainting algorithms have been previously proposed based on the assumption that an image can be modeled using autoregressive (AR) models. However, these algorithms perform poorly when applied to natural photographs because they assume that an image is modeled by a position-invariant linear model with a fixed model order. In order to improve inpainting quality, this work introduces a multiple AR model and proposes an image inpainting algorithm based on multiple matrix rank minimization with sparse regularization. In doing so, a practical algorithm is provided based on the iterative partial matrix shrinkage algorithm, with numerical examples showing the effectiveness of the proposed algorithm.},
keywords={},
doi={10.1587/transinf.2020EDP7086},
ISSN={1745-1361},
month={December},}
부
TY - JOUR
TI - Multiple Subspace Model and Image-Inpainting Algorithm Based on Multiple Matrix Rank Minimization
T2 - IEICE TRANSACTIONS on Information
SP - 2682
EP - 2692
AU - Tomohiro TAKAHASHI
AU - Katsumi KONISHI
AU - Kazunori URUMA
AU - Toshihiro FURUKAWA
PY - 2020
DO - 10.1587/transinf.2020EDP7086
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2020
AB - This paper proposes an image inpainting algorithm based on multiple linear models and matrix rank minimization. Several inpainting algorithms have been previously proposed based on the assumption that an image can be modeled using autoregressive (AR) models. However, these algorithms perform poorly when applied to natural photographs because they assume that an image is modeled by a position-invariant linear model with a fixed model order. In order to improve inpainting quality, this work introduces a multiple AR model and proposes an image inpainting algorithm based on multiple matrix rank minimization with sparse regularization. In doing so, a practical algorithm is provided based on the iterative partial matrix shrinkage algorithm, with numerical examples showing the effectiveness of the proposed algorithm.
ER -