Image compressive sensing reconstruction via nonlocal low-rank residual-based ADMM framework

Junhao Zhang, Kim Hui Yap, Lap Pui Chau, Ce Zhu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

The nonlocal low-rank (LR) modeling has proven to be an effective approach in image compressive sensing (CS) reconstruction, which starts by clustering similar patches using the nonlocal self-similarity (NSS) prior into nonlocal image group and then imposes an LR penalty on each nonlocal image group. However, most existing methods only approximate the LR matrix directly from the degraded nonlocal image group, which may lead to suboptimal LR matrix approximation and thus obtain unsatisfactory reconstruction results. In this paper, we propose a novel nonlocal low-rank residual (NLRR) approach for image CS reconstruction, which progressively approximates the underlying LR matrix by minimizing the LR residual. To do this, we first use the NSS prior to obtaining a good estimate of the original nonlocal image group, and then the LR residual between the degraded nonlocal image group and the estimated nonlocal image group is minimized to derive a more accurate LR matrix. To ensure the optimization is both feasible and reliable, we employ an alternative direction multiplier method (ADMM) to solve the NLRR-based image CS reconstruction problem. Our experimental results show that the proposed NLRR algorithm achieves superior performance against many popular or state-of-the-art image CS reconstruction methods, both in objective metrics and subjective perceptual quality.

Original languageEnglish
Article number104204
JournalComputer Vision and Image Understanding
Volume249
DOIs
Publication statusPublished - Dec 2024

Keywords

  • ADMM
  • Image compressive sensing reconstruction
  • Low-rank
  • Nonlocal low-rank residual
  • Nonlocal self-similarity

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Image compressive sensing reconstruction via nonlocal low-rank residual-based ADMM framework'. Together they form a unique fingerprint.

Cite this