Abstract

Single image super-resolution via convolutional neural network (CNN) has demonstrated superior performance. In this paper, we propose a deep CNN model named super-resolution dense residual convolutional network (SRDCR) with the goal of reconstructing high quality high-resolution (HR) image. We propose a dense residual block (DRB) to learn residual information by residual connected layers. The local fusion layer (LFL) is then used to adaptively fuse the input of DRB and the output of the last residual layer. After multiple DRBs residual learning, the global fusion layer (GFL) reconstructs an HR image by adaptively combining the original low-resolution (LR) information and learned information. Experiments on extensive benchmark show that our method achieves favorable performance with much less CNN layers than DRB network.

中文翻译：

---

基于密集残差卷积网络的单图像超分辨率算法

摘要

通过卷积神经网络（CNN）的单图像超分辨率已显示出卓越的性能。在本文中，我们提出了一个深CNN模型，称为超分辨率密集残差卷积网络（SRDCR），旨在重建高质量高分辨率（HR）图像。我们提出了一个密集的残差块（DRB），以通过残差连接层学习残差信息。然后，使用局部融合层（LFL）来自适应融合DRB的输入和最后一个残差层的输出。经过多次DRB残留学习后，全局融合层（GFL）通过自适应地组合原始低分辨率（LR）信息和学习到的信息来重建HR图像。大量基准测试表明，我们的方法具有比DRB网络少得多的CNN层的良好性能。