The Power of Triply Complementary Priors for Image Compressive Sensing

TL;DR

This paper introduces a hybrid plug-and-play framework leveraging triply complementary priors for improved image compressive sensing, combining deep and shallow, external and internal, local and non-local information.

Contribution

It proposes a novel joint low-rank and deep image model with triply complementary priors and a new optimization algorithm for effective image CS recovery.

Findings

Outperforms state-of-the-art methods like SCSNet and WNNM in image CS tasks.

Effectively leverages multiple priors to enhance image reconstruction quality.

Demonstrates robustness and superior performance across various experiments.

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