Lightweight Spatial-Channel Adaptive Coordination of Multilevel Refinement Enhancement Network for Image Reconstruction

TL;DR

This paper introduces a lightweight multilevel refinement network that adaptively coordinates spatial and channel features for image reconstruction, improving performance with fewer parameters and lower complexity.

Contribution

It proposes a novel spatial-channel adaptive coordination block and a communication bridge between attention modules, enhancing feature learning and information exchange.

Findings

Outperforms existing algorithms on standard test sets.

Uses fewer parameters and has lower computational complexity.

Achieves superior image reconstruction quality.

Abstract

Benefiting from the vigorous development of deep learning, many CNN-based image super-resolution methods have emerged and achieved better results than traditional algorithms. However, it is difficult for most algorithms to adaptively adjust the spatial region and channel features at the same time, let alone the information exchange between them. In addition, the exchange of information between attention modules is even less visible to researchers. To solve these problems, we put forward a lightweight spatial-channel adaptive coordination of multilevel refinement enhancement networks(MREN). Specifically, we construct a space-channel adaptive coordination block, which enables the network to learn the spatial region and channel feature information of interest under different receptive fields. In addition, the information of the corresponding feature processing level between the spatial part and the channel part is exchanged with the help of jump connection to achieve the coordination between the two. We establish a communication bridge between attention modules through a simple linear combination operation, so as to more accurately and continuously guide the network to pay attention to the information of interest. Extensive experiments on several standard test sets have shown that our MREN achieves superior performance over other advanced algorithms with a very small number of parameters and very low computational complexity.