激光与光电子学进展, 2020, 57 (18): 181009, 网络出版: 2020-09-02
基于多尺度与多重残差网络的图像超分辨率重建 下载: 897次
Super-Resolution Reconstruction of Images Based on Multi-Scale and Multi-Residual Network
图像处理 超分辨率 神经网络 多尺度特征 多重残差网络 image processing super-resolution neural network multi-scale features multi-residual network
摘要
近几年虽然基于神经网络的超分辨率重建技术发展迅速,但仍然存在不易找到合适尺寸的卷积核、网络层数过深导致收敛缓慢等缺点。为此,提出了一种能多尺度提取特征并包含多重残差的网络模型。低分辨率图像输入网络,通过多个多尺度残差模块,在每个模块进行多尺度特征提取、特征融合,构建残差输出到下一个模块,通过所有模块后再次构建残差,最终经过亚像素卷积输出高分辨率图像。实验结果表明,多重残差的引入使学习的收敛速度更快,多尺度能更好地提取图像特征,使图像在主观和客观度量上都优于其他主流算法。
Abstract
Recent years, although the super-resolution reconstruction technology based on neural network has developed rapidly, there are still some shortcomings, such as difficult to find the appropriate size of convolution kernel, and slow convergence speed caused by too deep network layers. In this paper, a model which can extract features at multiple scales and contains multi-residual structure is proposed. Low-resolution image is input to the network, through serial multi-scale residual blocks, extracted and concatenated features at multiple scales in each block, after residual structure the image outputs to the next block, after all blocks, builds residual again, and finally outputs high-resolution image through sub-pixel convolution. The experimental results show that the proposal of multi-residual structure makes faster convergence, and the multi-scale structure extracts image features better to make the image excel other mainstream algorithms in whether subjective or objective measurement.
陈星宇, 张伟劲, 孙伟智, 任萍安, 欧鸥. 基于多尺度与多重残差网络的图像超分辨率重建[J]. 激光与光电子学进展, 2020, 57(18): 181009. Xingyu Chen, Weijin Zhang, Weizhi Sun, Ping'an Ren, Ou Ou. Super-Resolution Reconstruction of Images Based on Multi-Scale and Multi-Residual Network[J]. Laser & Optoelectronics Progress, 2020, 57(18): 181009.