Hybrid Plug-and-Play Model for Image restoration

Citation Author(s):
Zhiyuan
Zha
Nanyang Technological University
Submitted by:
Zhiyuan Zha
Last updated:
Wed, 06/02/2021 - 12:14
DOI:
10.21227/a25e-6z74
License:
21 Views
Categories:
0
0 ratings - Please login to submit your rating.

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, \eg, 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, $\emph{internal}$ and $\emph{external}$, $\emph{shallow}$ and $\emph{deep}$, and $\emph{non-local}$ and $\emph{local}$ 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.

Instructions: 

DESCRIPTION: The supplementary files include a Matlab implemented code for readers.

 

SIZE: The total size of the file is 71.90MB PLAYER INFORMATION: Matlab 2016b PACKING LIST:

 

H_PnP_demo.zip

 

CONTACT INFORMATION: Zhiyuan Zha

 

School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798.

 

E-mail: zhiyuan.zha@ntu.edu.sg