Simultaneous image denoising and completion through convolutional sparse representation and nonlocal self-similarity

Weimin Yuan, Yuanyuan Wang, Ruirui Fan, Yuxuan Zhang, Guangmei Wei, Cai Meng, Xiangzhi Bai

Abstract: Highlights•Focusing on the task of simultaneous image denoising and completion, we propose a novel Low rank matrix approximation (LRMA) based method. The proposed method full leverages convolutional analysis sparse representation (ASR) and nonlocal statistical modeling (NLSM).•By exploiting the alternating direction method of multipliers (ADMM), the proposed method, which embeds three regularization terms into a unified framework, is solved efficiently.•Extensive experimental results demonstrate the superiority and generalizability of the proposed method by comparing it with seventeen state-of-the-art methods on four widely-used benchmarks and several challenging degradation scenarios.