Super-resolution using multi-channel merged convolutional network
Super-resolution using multi-channel merged convolutional network
复制标题
DOI：
10.1016/j.neucom.2019.04.089
复制
发表时间：
2020-06
期刊：
影响因子：
6
通讯作者：
Jinghui Chu;Xiaochuan Li;Jiaqi Zhang;W. Lu
中科院分区：
文献类型：
--
作者：
Jinghui Chu;Xiaochuan Li;Jiaqi Zhang;W. Lu
由于视觉人工智能领域对高质量虚拟图像的需求，单图像超分辨率（SISR）已成为一个重要的课题。基于深度学习的方法基于深度卷积网络对复杂特征的优异把握能力而取得了巨大成功。通过简单地加宽或加深网络，性能可以略有提高，但不明显。在本文中，我们提出了一种用于超分辨率的合并卷积网络，它可以提取更充分的细节来恢复高分辨率图像。我们使用密集块进行特征提取，以将深层特征与浅层特征深度连接起来。我们还设计了两个具有不同卷积核的子网作为网络的不同分支，这可以拓宽网络并提高系统的性能。最后，我们采用子像素层来避免最后上采样的特征失真。我们的方法使用几个标准基准数据集进行了评估。与最先进的方法相比，结果表明具有卓越的性能和良好的鲁棒性。
Single-image super-resolution (SISR) has been an important topic due to the demand for high-quality virtual images in the field of visual artificial intelligence. Methods based on deep learning have achieved great success based on the excellent capability of grasping complicated features of deep convolutional networks. The performance can be improved slightly but not obviously by simply widening or deepening the network. In this paper, we propose a merged convolutional network for super-resolution, which extracts more adequate details to restore high-resolution images. We used dense blocks for feature extraction to concatenate deep features with shallow features in depth. We also designed two sub-nets with distinct convolution kernels as different branches of the network, which can widen the network and improve the performance of the system. Finally, we employed sub-pixel layers to avoid feature distortion for up-sampling at the very end. Our method was evaluated using several standard benchmark datasets. The results demonstrate superior performance and good robustness compared with state-of-the-art methods.