摘要
针对残差学习的超分辨率重建方法中存在感受野受限、分辨率低、复杂性较高、边缘信息丢失等问题,提出一种锯齿空洞残差卷积的神经网络.首先,基于Res Net网络设计了锯齿空洞卷积,扩大网络的感受野,消除网络的"网格化",并增加跳跃连接,将图像特征传递到更深的网路;然后,通过最后一个卷积层得到与原始图像大小相等的残差图像;最后,将输入LR图像与残差图像进行线性融合输出最终的超分辨率图像.在set5和set14数据集上的实验数据表明:与现有算法相比,本文算法具有更好的重建效果,学习性能有较大提高.
In order to solve the problems of the limited receptive field,low-resolution,high complexity and loss of edge information in the super-resolution reconstruction method of residual learning,adilated residual convolution neural network is proposed.Firstly,we design the sawtooth dilated convolution based on the Res Net network to expand the receptive field of the network and eliminate the"zero filling"of the network,the image features are transferred to the deeper network by adding the jump connection.Secondly,the residual image with the same size as the original image is obtained through the last convolution layer.Finally,the input LR image and the residual image are linearly fused to output the final super-resolution image.The experimental data on set 5 and set 14 shows that compared with the existing algorithms,the algorithm of this paper has better reconstruction effect and better learning performance.
作者
李岚
蔺国梁
马少斌
LI Lan;LIN Guoliang;MA Shaobin(School of Digital Media,Lanzhou University of Arts and Science,Lanzhou Gansu 730000,China)
出处
《新疆大学学报（自然科学版）（中英文）》
2021年第2期174-190,共17页
Journal of Xinjiang University(Natural Science Edition in Chinese and English)
基金
2020年甘肃省高等教育教学成果培育项目
2019年甘肃省创新创业项目
2018年甘肃高等学校科研项目
2019年甘肃省教育厅产业支撑引导项目。
关键词
残差网络
锯齿空洞卷积
深度学习
图像超分辨率重建
residual network
dilated convolution
deep learning
image super-resolution reconstruction
