UM  > Faculty of Science and Technology
Affiliated with RCfalse
Status已發表Published
The Power of Triply Complementary Priors for Image Compressive Sensing
Zhiyuan Zha1; Xin Yuan2; Joey Tianyi Zhou3; Jiantao Zhou4; Bihan Wen1; Ce Zhu5
2020-09-30
Conference NameIEEE International Conference on Image Processing
Source PublicationProceedings - International Conference on Image Processing, ICIP
Volume2020-October
Pages983-987
Conference Date25-28 Oct. 2020
Conference PlaceAbu Dhabi, United Arab Emirates
Abstract

Recent works that utilized deep models have achieved superior results in various image restoration applications. Such approach is typically supervised which requires a corpus of training images with distribution similar to the images to be recovered. On the other hand, the shallow methods which are usually unsupervised remain promising performance in many inverse problems, e.g., image compressive sensing (CS), as they can effectively leverage non-local self-similarity priors of natural images. However, most of such methods are patch-based leading to the restored images with various ringing artifacts due to naive patch aggregation. Using either approach alone usually limits performance and generalizability in image restoration tasks. In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely external and internal, deep and shallow, and local and nonlocal priors. We then propose a novel hybrid plug-and-play (H-PnP) framework based on the LRD model for image CS. To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-PnP based image CS problem. Extensive experimental results demonstrate that the proposed H-PnP algorithm significantly outperforms the state-of-the-art techniques for image CS recovery such as SCSNet and WNNM.

KeywordDeep Prior Hybrid Plug-and-play Image Cs Non-local Self-similarity Triply Complementary Priors
DOI10.1109/ICIP40778.2020.9190707
URLView the original
Indexed ByCPCI-S
Language英語English
WOS Research AreaImaging Science & Photographic Technology
WOS SubjectImaging Science & Photographic Technology
Scopus ID2-s2.0-85090832228
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionFaculty of Science and Technology
Affiliation1.School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore 639798
2.Nokia Bell Labs, 600 Mountain Avenue, Murray Hill, NJ, 07974, USA.
3.Institute of High Performance Computing, A*STAR, Singapore 138632.
4.Department of Computer and Information Science, University of Macau, Macau 999078, China.
5.School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China
Recommended Citation
GB/T 7714
Zhiyuan Zha,Xin Yuan,Joey Tianyi Zhou,et al. The Power of Triply Complementary Priors for Image Compressive Sensing[C],2020:983-987.
APA Zhiyuan Zha,Xin Yuan,Joey Tianyi Zhou,Jiantao Zhou,Bihan Wen,&Ce Zhu.(2020).The Power of Triply Complementary Priors for Image Compressive Sensing.Proceedings - International Conference on Image Processing, ICIP,2020-October,983-987.
Files in This Item: Download All
File Name/Size Publications Version Access License
The_Power_Of_Triply_(238KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhiyuan Zha]'s Articles
[Xin Yuan]'s Articles
[Joey Tianyi Zhou]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhiyuan Zha]'s Articles
[Xin Yuan]'s Articles
[Joey Tianyi Zhou]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhiyuan Zha]'s Articles
[Xin Yuan]'s Articles
[Joey Tianyi Zhou]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: The_Power_Of_Triply_Complementary_Priors_For_Image_Compressive_Sensing.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.