A Tree-Guided CNN for Image Super-Resolution

2025-06-03

IEEE transactions on consumer electronics

AI Summary

To address insufficient hierarchical feature modeling and weak influence of critical nodes in image super-resolution, this paper proposes the Tree-guided Super-Resolution Network (TSRNet). Methodologically: (1) a tree-like topology is explicitly designed to model cross-level feature dependencies and enhance the contribution of critical nodes to reconstruction; (2) discrete cosine transform (DCT) is integrated to incorporate structural frequency-domain information, mitigating CNNs’ limitations in modeling long-range correlations; (3) the Adan optimizer is adopted to improve training stability and convergence speed. Evaluated on standard benchmarks—including Set5, Set14, and Urban100—TSRNet consistently outperforms state-of-the-art methods such as EDSR and RCAN, achieving average PSNR gains of 0.25–0.42 dB and corresponding SSIM improvements. The source code is publicly released and experimentally verified for reproducibility.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Data and user privacy-enhancing technologies for the Web

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.

Problem

• Enhances key node effects in deep networks for image super-resolution
• Uses cosine transform to extract cross-domain structural information
• Optimizes training with adaptive Nesterov momentum for better performance

Innovation

• Tree-guided CNN enhances key node effects
• Cosine transform extracts cross-domain information
• Adan optimizer boosts training effectiveness