一种多映射卷积神经网络的超分辨率重建算法

doi:10.3969/j.issn.1001-2400.2018.04.027

摘要/Abstract

摘要：

针对现有卷积神经网络在超分辨率重建的图像上存在部分细节特征不够突出、边缘模糊等问题，在现有模型三大模块的基础上对映射模块及损失函数进行细致剖析，提出了一种多映射卷积神经网络的超分辨率重建算法．该算法通过构建多映射网络，极大地丰富了图像在聚合高分辨图像时的特征维度．同时在重建模块的卷积层后引入全变分正则项，结合误差反向传播算法，可有效地对解空间约束，从而提取出精确、有效的特征，丰富重建图像的细节信息．在常用数据集上的实验结果表明，该算法生成的网络模型获得了更好的超分辨率结果，主观视觉评价和客观衡量指标有一定的改进，有效地提高了图像的分辨率．

关键词: 图像处理, 超分辨率, 多映射卷积神经网络, 变分约束

Abstract:

The traditional convolutional neural network for super-resolution will obtain abundant details and edge information with difficulty. By the analysis of the detailed characteristics in three modules of conventional methods, we propose a new multi-mapping convolutional neural network model. By the multi-mapping module, rich and varied characteristics from each layer can be captured. Combining with the error back propagation algorithm, a novel loss function with total variation regularization is used to train and seek optimal parameters, which reconstruct accurate and effective high-resolution images from the network. Extensive quantitative and qualitative evaluations have shown that the proposed algorithm improves effectively the resolution of the image.

Key words: image processing, super-resolution, multi-mapping convolutional network, constrained variation method

王世平;毕笃彦;刘坤;何林远. 一种多映射卷积神经网络的超分辨率重建算法[J]. 西安电子科技大学学报, 2018, 45(4): 155-160.

WANG Shiping;BI Duyan;LIU Kun;HE Linyuan. Multi-mapping convolution neural network for the image super-resolution algorithm[J]. Journal of Xidian University, 2018, 45(4): 155-160.

参考文献

［1］ HU Y, WANG N, TAO D, et al. SERF: a Simple, Effective, Robust, and Fast Image Super-resolvtion from Cascaded Linear Regression［J］. IEEE Transactions on Image Processing, 2016, 25(9): 4091-4102.
［2］苏衡, 周杰, 张志浩, 等. 超分辨率图像重建方法综述［J］. 自动化学报, 2013, 39(8): 1202-1213.
SU Heng, ZHOU Jie, ZHANG Zhihao, et al. Survey of Super-resolution Image Reconstruction Methods［J］. Acta Automatica Sinica, 2013, 39(8): 1202-1213.
［3］ CHOI J S, BAE S H, KIM M. Single Image Super-resolution Based on Self-examples Using Context-dependent Subpatches［C］//Proceedings of the 2015 International Conference on Image Processing. Washington: IEEE Computer Society, 2015: 2835-2839.
［4］ SCHUON S, THEOBALT C, DAVIS J, et al. LidarBoost: Depth Superresolution for ToF 3D Shape Scanning［C］//Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Washington: IEEE Computer Society, 2009: 343-350.
［5］ DONG C, LOY C C, HE K, et al. Image Super-resolution Using Deep Convolutional Networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307.
［6］ KIM J, LEE J K, LEE K M. Accurate Image Super-resolution Using Very Deep Convolutional Network［C］//Proceedings of the 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2016: 1646-1654.
［7］ KIM J, LEE J K, LEE K M. Deeply-recursive Convolution Network for Image Super-resolution［C］//Proceedings of the 2016 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2016: 1637-1645.
［8］ GOLDSTEIN T, OSCHER S. The Split Bregman Method for L₁ Regularized Problem［J］. SIAM Journal on Imaging Sciences, 2009, 2(2): 323-343.
［9］ LEDIG C, THEIS L, HUSSARS F, et al. Photo-realistic Single Image Super-resolution Using a Generative Adversarial Network［C］//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2017: 543-551.
［10］ MARTIN D, FOWLKES C, TAL D, et al. A Database of Human Segmented Natural Images and Its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics［C］//Proceedings of the 2001 IEEE Conference on International Conference on Computer Vision. Washington: IEEE Computer Society, 2001: 416-423.

[1]	张宇浩,程培涛,张书豪,王秀美. 一种自适应权重学习的轻量超分辨率重建网络[J]. 西安电子科技大学学报, 2021, 48(5): 15-22.
[2]	韩永赛,马时平,何林远,李承昊,朱明明,张飞. 改进YOLOv3的快速遥感机场区域目标检测[J]. 西安电子科技大学学报, 2021, 48(5): 156-166.
[3]	詹克羽,孙岳,李颖. 一种多尺度三维卷积的视频超分辨率方法[J]. 西安电子科技大学学报, 2021, 48(5): 8-14.
[4]	孙正阳,董玫,陈伯孝. 时频分析联合带通滤波抑制间歇采样转发干扰[J]. 西安电子科技大学学报, 2021, 48(2): 139-146.
[5]	崔艳鹏,王元皓,胡建伟. 一种改进YOLOv3的动态小目标检测方法[J]. 西安电子科技大学学报, 2020, 47(3): 1-7.
[6]	成天佑,林艳萍,马晓军. 一种视触觉引导的超声探头自动定位方法[J]. 西安电子科技大学学报, 2020, 47(1): 80-87.
[7]	汪梓艺,苏育挺,刘艳艳,张为. 一种改进DeeplabV3网络的烟雾分割算法[J]. 西安电子科技大学学报, 2019, 46(6): 52-59.
[8]	欧阳宁,王先傲,蔡晓东,林乐平. 结合小波与递归神经网络的低分辨率人脸识别[J]. 西安电子科技大学学报, 2019, 46(6): 95-101.
[9]	刘树东,王晓敏,张艳. 一种对称残差CNN的图像超分辨率重建方法[J]. 西安电子科技大学学报, 2019, 46(5): 15-23.
[10]	朱苏雅,杜建超,李云松,汪小鹏. 采用U-Net卷积网络的桥梁裂缝检测方法[J]. 西安电子科技大学学报, 2019, 46(4): 35-42.
[11]	张锦涛,雷杰,吴凌云,黄碧莹,李云松. 一种改进的高光谱端元提取算法及其FPGA实现[J]. 西安电子科技大学学报, 2019, 46(4): 22-27.
[12]	陈晓范,申海杰,边倩,王振铎,田新志. 结合注意力机制的人脸超分辨率重建[J]. 西安电子科技大学学报, 2019, 46(3): 148-153.
[13]	时文俊,郭从洲,童晓冲,田园,曹闻. 辐射保真的红外遥感图像超分辨率重建[J]. 西安电子科技大学学报, 2019, 46(2): 107-113.
[14]	赖睿,官俊涛,徐昆然,熊皑,杨银堂. 级联残差学习的红外图像非均匀性校正方法[J]. 西安电子科技大学学报, 2019, 46(1): 14-19.
[15]	郭松鸽;吕东辉;任艳丽. 一种改进的(k, n)标记视觉密码方案[J]. 西安电子科技大学学报, 2018, 45(5): 170-176+183.