用树形结构引导网络，提升图像超分辨率的细节恢复能力
A Tree-guided CNN for image super-resolution
- 设计树形架构引导深层网络增强关键节点作用
- 融合余弦变换提取跨域信息，提升结构重建效果
- 采用自适应优化器加速训练，适合图像重建研究者
深度卷积神经网络通过深层结构可提取更精确的图像结构信息，在图像超分辨率任务中表现优异。然而，单个网络架构中关键层的作用难以有效识别，可能影响重建性能。本文提出一种树引导的卷积神经网络（TSRNet），利用树形结构指导深层网络，强化关键节点的影响，增强层次化信息关联性，提升图像恢复能力。为弥补结构信息不足，TSRNet引入余弦变换技术提取跨域特征，进一步优化重建效果。同时采用自适应Nesterov动量优化器（Adan）进行参数优化，显著提升训练效率。大量扩展实验验证了该方法在恢复高质量图像方面的优越性。代码已开源：https://github.com/hellloxiaotian/TSRNet。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。