Efficient Scale-Recurrent Network Using Generative Adversarial Network for Image Deblurring

Wei Hsiang Hsu; Chih Wei Tang

doi:10.1109/ICCE53296.2022.9730407

Efficient Scale-Recurrent Network Using Generative Adversarial Network for Image Deblurring

Wei Hsiang Hsu, Chih Wei Tang

通訊工程學系

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

1 引文斯高帕斯（Scopus）

摘要

Ubiquitous blurry images degrade viewing experiences and performance of video analysis. To be applicable to consumer electronics, the large amount of parameters and high computational load of deblurring network have to be avoided. The existing SRN+ has a small number of parameters (3.9M) and comparable performance. To improve the quality of outputs of a deblurring network (e.g., SRN+) without changing its architecture, this paper proposes the pseudo label based order task for training the discriminator. The proposed funnel soft label further reduces the problem of vanishing gradient during training SRN+ (generator), and the adversarial loss combined with weighted scale-level losses improves quality of deblurring. For GoPro dataset, the proposed scheme outperforms the light version of the state-of-the-art MPRNet in PSNR (+1dB) and number of parameters (70%).

原文	???core.languages.en_GB???
主出版物標題	2022 IEEE International Conference on Consumer Electronics, ICCE 2022
發行者	Institute of Electrical and Electronics Engineers Inc.
ISBN（電子）	9781665441544
DOIs	https://doi.org/10.1109/ICCE53296.2022.9730407
出版狀態	已出版 - 2022
事件	2022 IEEE International Conference on Consumer Electronics, ICCE 2022 - Virtual, Online, United States 持續時間: 7 1月 2022 → 9 1月 2022

出版系列

名字	Digest of Technical Papers - IEEE International Conference on Consumer Electronics
卷	2022-January
ISSN（列印）	0747-668X

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	2022 IEEE International Conference on Consumer Electronics, ICCE 2022
國家/地區	United States
城市	Virtual, Online
期間	7/01/22 → 9/01/22

存取文件

10.1109/ICCE53296.2022.9730407

基於生成對抗網路之視覺追蹤
Tang, C.-W. (PI)
1/08/20 → 31/07/21
研究計畫: Research
基於深度學習之360度視訊分析與處理
Tang, C.-W. (PI)
1/08/19 → 31/07/20
研究計畫: Research

引用此

Hsu, W. H., & Tang, C. W. (2022). Efficient Scale-Recurrent Network Using Generative Adversarial Network for Image Deblurring. 於 2022 IEEE International Conference on Consumer Electronics, ICCE 2022 (Digest of Technical Papers - IEEE International Conference on Consumer Electronics; 卷 2022-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE53296.2022.9730407

@inproceedings{c154ad09217e440bb54ec06f88b7f40b,

title = "Efficient Scale-Recurrent Network Using Generative Adversarial Network for Image Deblurring",

abstract = "Ubiquitous blurry images degrade viewing experiences and performance of video analysis. To be applicable to consumer electronics, the large amount of parameters and high computational load of deblurring network have to be avoided. The existing SRN+ has a small number of parameters (3.9M) and comparable performance. To improve the quality of outputs of a deblurring network (e.g., SRN+) without changing its architecture, this paper proposes the pseudo label based order task for training the discriminator. The proposed funnel soft label further reduces the problem of vanishing gradient during training SRN+ (generator), and the adversarial loss combined with weighted scale-level losses improves quality of deblurring. For GoPro dataset, the proposed scheme outperforms the light version of the state-of-the-art MPRNet in PSNR (+1dB) and number of parameters (70%).",

keywords = "Image deblurring, generative adversarial networks (GAN), loss function, pseudo label, scale recurrent network",

author = "Hsu, {Wei Hsiang} and Tang, {Chih Wei}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Consumer Electronics, ICCE 2022 ; Conference date: 07-01-2022 Through 09-01-2022",

year = "2022",

doi = "10.1109/ICCE53296.2022.9730407",

language = "???core.languages.en_GB???",

series = "Digest of Technical Papers - IEEE International Conference on Consumer Electronics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 IEEE International Conference on Consumer Electronics, ICCE 2022",

}

Hsu, WH & Tang, CW 2022, Efficient Scale-Recurrent Network Using Generative Adversarial Network for Image Deblurring. 於 2022 IEEE International Conference on Consumer Electronics, ICCE 2022. Digest of Technical Papers - IEEE International Conference on Consumer Electronics, 卷 2022-January, Institute of Electrical and Electronics Engineers Inc., 2022 IEEE International Conference on Consumer Electronics, ICCE 2022, Virtual, Online, United States, 7/01/22. https://doi.org/10.1109/ICCE53296.2022.9730407

Efficient Scale-Recurrent Network Using Generative Adversarial Network for Image Deblurring. / Hsu, Wei Hsiang; Tang, Chih Wei.
2022 IEEE International Conference on Consumer Electronics, ICCE 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (Digest of Technical Papers - IEEE International Conference on Consumer Electronics; 卷 2022-January).

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

TY - GEN

T1 - Efficient Scale-Recurrent Network Using Generative Adversarial Network for Image Deblurring

AU - Hsu, Wei Hsiang

AU - Tang, Chih Wei

PY - 2022

Y1 - 2022

N2 - Ubiquitous blurry images degrade viewing experiences and performance of video analysis. To be applicable to consumer electronics, the large amount of parameters and high computational load of deblurring network have to be avoided. The existing SRN+ has a small number of parameters (3.9M) and comparable performance. To improve the quality of outputs of a deblurring network (e.g., SRN+) without changing its architecture, this paper proposes the pseudo label based order task for training the discriminator. The proposed funnel soft label further reduces the problem of vanishing gradient during training SRN+ (generator), and the adversarial loss combined with weighted scale-level losses improves quality of deblurring. For GoPro dataset, the proposed scheme outperforms the light version of the state-of-the-art MPRNet in PSNR (+1dB) and number of parameters (70%).

AB - Ubiquitous blurry images degrade viewing experiences and performance of video analysis. To be applicable to consumer electronics, the large amount of parameters and high computational load of deblurring network have to be avoided. The existing SRN+ has a small number of parameters (3.9M) and comparable performance. To improve the quality of outputs of a deblurring network (e.g., SRN+) without changing its architecture, this paper proposes the pseudo label based order task for training the discriminator. The proposed funnel soft label further reduces the problem of vanishing gradient during training SRN+ (generator), and the adversarial loss combined with weighted scale-level losses improves quality of deblurring. For GoPro dataset, the proposed scheme outperforms the light version of the state-of-the-art MPRNet in PSNR (+1dB) and number of parameters (70%).

KW - Image deblurring

KW - generative adversarial networks (GAN)

KW - loss function

KW - pseudo label

KW - scale recurrent network

UR - http://www.scopus.com/inward/record.url?scp=85127032749&partnerID=8YFLogxK

U2 - 10.1109/ICCE53296.2022.9730407

DO - 10.1109/ICCE53296.2022.9730407

M3 - 會議論文篇章

AN - SCOPUS:85127032749

T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics

BT - 2022 IEEE International Conference on Consumer Electronics, ICCE 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Consumer Electronics, ICCE 2022

Y2 - 7 January 2022 through 9 January 2022

ER -

Efficient Scale-Recurrent Network Using Generative Adversarial Network for Image Deblurring

摘要

出版系列

???event.eventtypes.event.conference???

存取文件

指紋

專案

基於生成對抗網路之視覺追蹤

基於深度學習之360度視訊分析與處理

引用此