A Tree-guided CNN for image super-resolution

TL;DR

This paper introduces TSRNet, a tree-guided CNN that leverages hierarchical structure and cross-domain information to enhance image super-resolution performance, optimized with Adan for better training efficiency.

Contribution

The paper proposes a novel tree-guided CNN architecture with cosine transform and Adan optimizer for improved image super-resolution.

Findings

TSRNet outperforms existing methods in image quality restoration.

Hierarchical tree architecture enhances key feature extraction.

Cross-domain information improves super-resolution accuracy.

Abstract

Deep convolutional neural networks can extract more accurate structural information via deep architectures to obtain good performance in image super-resolution. However, it is not easy to find effect of important layers in a single network architecture to decrease performance of super-resolution. In this paper, we design a tree-guided CNN for image super-resolution (TSRNet). It uses a tree architecture to guide a deep network to enhance effect of key nodes to amplify the relation of hierarchical information for improving the ability of recovering images. To prevent insufficiency of the obtained structural information, cosine transform techniques in the TSRNet are used to extract cross-domain information to improve the performance of image super-resolution. Adaptive Nesterov momentum optimizer (Adan) is applied to optimize parameters to boost effectiveness of training a super-resolution model. Extended experiments can verify superiority of the proposed TSRNet for restoring high-quality images. Its code can be obtained at https://github.com/hellloxiaotian/TSRNet.