Dynamically unfolding recurrent restorer: A moving endpoint control method for image restoration

Xiaoshuai Zhang; Jiaying Liu; Yiping Lu; Bin Dong

Dynamically unfolding recurrent restorer: A moving endpoint control method for image restoration

Xiaoshuai Zhang
, Jiaying Liu
, Yiping Lu
, Bin Dong

Hydrology & Atmospheric Sci

Research output: Contribution to conference › Paper › peer-review

19 Scopus citations

Abstract

In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels using a single model. The proposed control problem contains an image restoration dynamic which is modeled by a convolutional RNN. The moving endpoint, which is essentially the terminal time of the associated dynamic, is determined by a policy network. We call the proposed model the dynamically unfolding recurrent restorer (DURR). Numerical experiments show that DURR is able to achieve state-of-the-art performances on blind image denoising and JPEG image deblocking. Furthermore, DURR can well generalize to images with higher degradation levels that are not included in the training stage.

Original language	English (US)
State	Published - 2019
Event	7th International Conference on Learning Representations, ICLR 2019 - New Orleans, United States Duration: May 6 2019 → May 9 2019

Conference

Conference	7th International Conference on Learning Representations, ICLR 2019
Country/Territory	United States
City	New Orleans
Period	5/6/19 → 5/9/19

ASJC Scopus subject areas

Education
Computer Science Applications
Linguistics and Language
Language and Linguistics

Cite this

@conference{d42f2a7f4be14680b53a279e6831d007,

title = "Dynamically unfolding recurrent restorer: A moving endpoint control method for image restoration",

abstract = "In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels using a single model. The proposed control problem contains an image restoration dynamic which is modeled by a convolutional RNN. The moving endpoint, which is essentially the terminal time of the associated dynamic, is determined by a policy network. We call the proposed model the dynamically unfolding recurrent restorer (DURR). Numerical experiments show that DURR is able to achieve state-of-the-art performances on blind image denoising and JPEG image deblocking. Furthermore, DURR can well generalize to images with higher degradation levels that are not included in the training stage.",

author = "Xiaoshuai Zhang and Jiaying Liu and Yiping Lu and Bin Dong",

note = "Funding Information: Bin Dong is supported in part by Beijing Natural Science Foundation (Z180001).Yiping Lu is supported by the Elite Undergraduate Training Program of the School of Mathematical Sciences at Peking University. Publisher Copyright: {\textcopyright} 7th International Conference on Learning Representations, ICLR 2019. All Rights Reserved.; 7th International Conference on Learning Representations, ICLR 2019 ; Conference date: 06-05-2019 Through 09-05-2019",

year = "2019",

language = "English (US)",

}

TY - CONF

T1 - Dynamically unfolding recurrent restorer

T2 - 7th International Conference on Learning Representations, ICLR 2019

AU - Zhang, Xiaoshuai

AU - Liu, Jiaying

AU - Lu, Yiping

AU - Dong, Bin

N1 - Funding Information: Bin Dong is supported in part by Beijing Natural Science Foundation (Z180001).Yiping Lu is supported by the Elite Undergraduate Training Program of the School of Mathematical Sciences at Peking University. Publisher Copyright: © 7th International Conference on Learning Representations, ICLR 2019. All Rights Reserved.

PY - 2019

Y1 - 2019

N2 - In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels using a single model. The proposed control problem contains an image restoration dynamic which is modeled by a convolutional RNN. The moving endpoint, which is essentially the terminal time of the associated dynamic, is determined by a policy network. We call the proposed model the dynamically unfolding recurrent restorer (DURR). Numerical experiments show that DURR is able to achieve state-of-the-art performances on blind image denoising and JPEG image deblocking. Furthermore, DURR can well generalize to images with higher degradation levels that are not included in the training stage.

AB - In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels using a single model. The proposed control problem contains an image restoration dynamic which is modeled by a convolutional RNN. The moving endpoint, which is essentially the terminal time of the associated dynamic, is determined by a policy network. We call the proposed model the dynamically unfolding recurrent restorer (DURR). Numerical experiments show that DURR is able to achieve state-of-the-art performances on blind image denoising and JPEG image deblocking. Furthermore, DURR can well generalize to images with higher degradation levels that are not included in the training stage.

UR - https://www.scopus.com/pages/publications/85083952854

UR - https://www.scopus.com/pages/publications/85083952854#tab=citedBy

M3 - Paper

Y2 - 6 May 2019 through 9 May 2019

ER -

Dynamically unfolding recurrent restorer: A moving endpoint control method for image restoration

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this