UM  > Faculty of Science and Technology
Affiliated with RCfalse
Status已發表Published
Triply Complementary Priors for Image Restoration
Zha, Zhiyuan1; Wen, Bihan1; Yuan, Xin2; Zhou, Joey Tianyi3; Zhou, Jiantao4; Zhu, Ce5
2021
Source PublicationIEEE Transactions on Image Processing
ISSN1057-7149
Volume30Pages:5819-5834
Abstract

Recent works that utilized deep models have achieved superior results in various image restoration (IR) applications. Such approach is typically supervised, which requires a corpus of training images with distributions 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 deblurring and image compressive sensing (CS), as they can effectively leverage nonlocal self-similarity priors of natural images. However, most of such methods are patch-based leading to the restored images with various artifacts due to naive patch aggregation in addition to the slow speed. Using either approach alone usually limits performance and generalizability in IR tasks. In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely, internal and external, shallow and deep, and non-local and local priors. We then propose a novel hybrid plug-and-play (H-PnP) framework based on the LRD model for IR. Following this, a simple yet effective algorithm is developed to solve the proposed H-PnP based IR problems. Extensive experimental results on several representative IR tasks, including image deblurring, image CS and image deblocking, demonstrate that the proposed H-PnP algorithm achieves favorable performance compared to many popular or state-of-the-art IR methods in terms of both objective and visual perception.

KeywordDeep Models Hybrid Plug-and-play Image Restoration Low-rank Nonlocal Self-similarity Triply Complementary Priors
DOI10.1109/TIP.2021.3086049
URLView the original
Language英語English
Scopus ID2-s2.0-85110250643
Fulltext Access
Citation statistics
Cited Times [WOS]:11   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionFaculty of Science and Technology
Affiliation1.School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
2.Nokia Bell Labs, Berkeley Heights, United States
3.Institute of High Performance Computing, A∗STAR, Singapore, Singapore
4.Department of Computer and Information Science, State Key Laboratory of Internet of Things for Smart City, University of Macau, Taipa, Macao
5.School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
Recommended Citation
GB/T 7714
Zha, Zhiyuan,Wen, Bihan,Yuan, Xin,et al. Triply Complementary Priors for Image Restoration[J]. IEEE Transactions on Image Processing,2021,30:5819-5834.
APA Zha, Zhiyuan,Wen, Bihan,Yuan, Xin,Zhou, Joey Tianyi,Zhou, Jiantao,&Zhu, Ce.(2021).Triply Complementary Priors for Image Restoration.IEEE Transactions on Image Processing,30,5819-5834.
MLA Zha, Zhiyuan,et al."Triply Complementary Priors for Image Restoration".IEEE Transactions on Image Processing 30(2021):5819-5834.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zha, Zhiyuan]'s Articles
[Wen, Bihan]'s Articles
[Yuan, Xin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zha, Zhiyuan]'s Articles
[Wen, Bihan]'s Articles
[Yuan, Xin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zha, Zhiyuan]'s Articles
[Wen, Bihan]'s Articles
[Yuan, Xin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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