A Tree-guided CNN for image super-resolution
This work addresses the problem of improving image super-resolution for applications like computer vision, but it appears incremental as it builds on existing CNN methods with specific architectural tweaks.
The paper tackles image super-resolution by proposing TSRNet, a tree-guided CNN that enhances key nodes and uses cosine transforms to improve structural information recovery, achieving superior performance in restoring high-quality images as verified by experiments.
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.