MSPNet: Multi-stage progressive network for image denoising

• Published in: Neurocomputing (Amsterdam) Vol. 517; pp. 71 - 80
• Main Authors: Bai, Yu, Liu, Meiqin, Yao, Chao, Lin, Chunyu, Zhao, Yao
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 14.01.2023
• Subjects: Criss-cross attention; Encoder-decoder; Image denoising; Multi-stage; Criss-cross attention; Encoder-decoder; Multi-stage; Image denoising
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2022.09.098

Image denoising which aims to restore a high-quality image from the noisy version is one of the most challenging tasks in the low-level computer vision tasks. In this paper, we propose a multi-stage progressive denoising network (MSPNet) and decompose the denoising task into some sub-tasks to progressively remove noise. Specifically, MSPNet is composed of three denoising stages. Each stage combines a feature extraction module (FEM) and a mutual-learning fusion module (MFM). In the feature extraction module, an encoder-decoder architecture is employed to learn non-local contextualized features, and the channel attention blocks (CAB) are utilized to retain the local information of the image. In the mutual-learning fusion module, the criss-cross attention is introduced to balance the image spatial details and the contextualized information. Compared with the state-of-the-art works, experimental results show that MSPNet achieves notable improvements on both objective and subjective evaluations.