Image Reconstruction of Multi Branch Feature Multiplexing Fusion Network with Mixed Multi-layer Attention

TL;DR

This paper introduces a multi-branch feature fusion network with multi-layer attention and a lightweight residual channel attention mechanism to enhance image super-resolution, focusing on better feature utilization and detail restoration.

Contribution

The paper proposes a novel multi-branch feature multiplexing fusion network with mixed multi-layer attention and a lightweight residual channel attention module for improved image super-resolution.

Findings

Achieves superior objective metrics compared to existing methods.

Restores more detailed textures and edges in reconstructed images.

Demonstrates effectiveness on multiple benchmark datasets.

Abstract

Image super-resolution reconstruction achieves better results than traditional methods with the help of the powerful nonlinear representation ability of convolution neural network. However, some existing algorithms also have some problems, such as insufficient utilization of phased features, ignoring the importance of early phased feature fusion to improve network performance, and the inability of the network to pay more attention to high-frequency information in the reconstruction process. To solve these problems, we propose a multi-branch feature multiplexing fusion network with mixed multi-layer attention (MBMFN), which realizes the multiple utilization of features and the multistage fusion of different levels of features. To further improve the networks performance, we propose a lightweight enhanced residual channel attention (LERCA), which can not only effectively avoid the loss of channel information but also make the network pay more attention to the key channel information and benefit from it. Finally, the attention mechanism is introduced into the reconstruction process to strengthen the restoration of edge texture and other details. A large number of experiments on several benchmark sets show that, compared with other advanced reconstruction algorithms, our algorithm produces highly competitive objective indicators and restores more image detail texture information.