用于图像超分辨率重建的双通道残差网络

左龙; 张鹏; 荆树旭; 赵一; 李凡

doi:10.7652/xjtuxb202201018

您当前的位置：

首页 >

文章列表页 >

用于图像超分辨率重建的双通道残差网络

更新时间：2025-05-08

- 用于图像超分辨率重建的双通道残差网络
- Dual-Channel Residual Network for Image Super-Resolution Reconstruction
- 西安交通大学学报 2022年56卷第1期页码：158-164
- 作者机构：
  
  长安大学信息工程学院,西安,710054
- 作者简介：
- 基金信息：
  
  : 2021-05-12。作者简介: 左龙(1988—),男,讲师;李凡(通信作者),男,教授。基金项目: 国家自然科学基金资助项目(62071369)
- DOI：10.7652/xjtuxb202201018
  中图分类号： TP391.41
- 网络首发：2022-01-10，
  
  纸质出版：2022
- 稿件说明：
移动端阅览
左龙, 张鹏, 荆树旭, 等. 用于图像超分辨率重建的双通道残差网络[J]. 西安交通大学学报, 2022,56(1):158-164.

Dual-Channel Residual Network for Image Super-Resolution Reconstruction[J]. 2022, 56(1): 158-164.
左龙, 张鹏, 荆树旭, 等. 用于图像超分辨率重建的双通道残差网络[J]. 西安交通大学学报, 2022,56(1):158-164. DOI： 10.7652/xjtuxb202201018.

Dual-Channel Residual Network for Image Super-Resolution Reconstruction[J]. 2022, 56(1): 158-164. DOI： 10.7652/xjtuxb202201018.

摘要

针对现有基于深度学习的自然图像超分辨率算法在图像高频细节重建方面的不足

提出了一种更注重图像高频细节重建的双通道残差网络。使用带有通道注意力机制的残差结构作为网络的主通道; 为了在重建过程中更好地保留原始图像的几何结构和边缘信息

使用自适应结构化卷积设计了网络的辅助通道

以此构建的双通道残差网络在学习过程中会有更强的高频信息捕获能力; 为了使重建图像效果更加符合人眼的主观视觉感受

结合使用L

损失函数和多尺度结构相似度损失函数来训练网络

使网络在训练过程中能够较好地保留图像的视觉效果。实验结果表明:在主通道外并构基于结构化卷积的辅助通道可以使重建图像的峰值信噪比提高2 dB; 结合使用L

损失函数和多尺度结构相似度损失函数可以使重建图像的峰值信噪比提高3 dB、结构相似性提高0.5; 与同类网络客观定量相比

所提网络在两个公开数据集上取得的效果更优。

Abstract

Aiming at the shortcomings of the existing deep learning based image super-resolution algorithms in image high-frequency detail reconstruction

a dual-channel residual network emphasizing image high-frequency detail reconstruction is proposed. Residual structure with channel attention mechanism is leveraged as the main channel of the network. Targeting on retaining more delicate geometric structure and edge information of the original image during the reconstruction

the auxiliary channel of the network is designed by an adaptive structured convolution hence the evolved dual-channel residual network has a stronger ability to capture high-frequency information during the learning process. To make the reconstructed image we

ll coincide with the subjective visual experience of human eye

loss function is combined with the multi-scale structural similarity loss function to train the network

so that the network completely retains the visual effect of the image during the training process. Experiments on the benchmark database show that combining the auxiliary channel based on adaptive structured convolution outside the main channel can heighten the peak signal-to-noise ratio of the reconstructed image by 2 dB. The simultaneous operation of L

loss function and the multi-scale structural similarity loss function can heighten the peak signal-to-noise ratio of the reconstructed image by 3 dB and the structural similarity by 0.05. The objective and quantitative comparison with the competing networks exhibits the proposed network's outstanding effectiveness on two public data sets.

关键词

Keywords

references

张哲, 齐春, 张钊强, 等. 人脸超分辨率重建中投影空间的选择方法 [J]. 西安交通大学学报, 2018, 52(8): 43-48.

ZHANG Zhe, QI Chun, ZHANG Zhaoqiang, et al. A selection method of projection space for face super-resolution reconstruction [J]. Journal of Xi'an Jiaotong University, 2018, 52(8): 43-48.

宋长明, 王赟. 融合低秩和稀疏表示的图像超分辨率重建算法 [J]. 西安交通大学学报, 2018, 52(7): 18-24.

SONG Changming, WANG Yun. Super resolution reconstruction algorithm combined low rank with sparse representation [J]. Journal of Xi'an Jiaotong University, 2018, 52(7): 18-24.

李玉花, 齐春. 利用位置字典对的人脸图像超分辨率方法 [J]. 西安交通大学学报, 2012, 46(6): 7-11.

LI Yuhua, QI Chun. A super-resolution method for face images using position-dictionary pairs [J]. Journal of Xi'an Jiaotong University, 2012, 46(6): 7-11.

马祥, 齐春. 全局重建和位置块残差补偿的人脸图像超分辨率算法 [J]. 西安交通大学学报, 2010, 44(4): 9-12.

MA Xiang, QI Chun. A face image super-resolution algorithm based on global reconstruction and position-patch residue compensation [J]. Journal of Xi'an Jiaotong University, 2010, 44(4): 9-12.

付利华, 孙晓威, 赵宇, 等. 基于运动特征融合的快速视频超分辨率重构方法 [J]. 模式识别与人工智能, 2019, 32(11): 1022-1031.

FU Lihua, SUN Xiaowei, ZHAO Yu, et al. Fast video super-resolution reconstruction method based on motion feature fusion [J]. Pattern Recognition and Artificial Intelligence, 2019, 32(11): 1022-1031.

LEDIG C, THEIS L, HUSZÁR 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(CVPR). Piscataway, NJ, USA: IEEE, 2017: 105-114.

SHI Wenzhe, CABALLERO J, LEDIG C, et al. Cardiac image super-resolution with global correspondence using multi-atlas patchmatch [C]∥Proceedings of the 2013 Medical Image Computing and Computer-Assisted Intervention(MICCAI). Cham, Germany: Springer, 2013: 9-16.

KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks [C]∥Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2016: 1646-1654.

ZHANG Yulun, LI Kunpeng, LI Kai, et al. Image super-resolution using very deep residual channel attention networks [C]∥Proceedings of the 2018 European Conference on Computer Vision(ECCV). Cham, Germany: Springer, 2018: 294-310.

DONG Chao, LOY C C, HE Kaiming, et al. Learning a deep convolutional network for image super-resolution [C]∥Proceedings of the 2014 European Conference on Computer Vision(ECCV). Cham, Germany: Springer, 2014: 184-199.

TAI Ying, YANG Jian, LIU Xiaoming. Image super-resolution via deep recursive residual network [C]∥Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2017: 2790-2798.

TAI Ying, YANG Jian, LIU Xiaoming, et al. MemNet: a persistent memory network for image restoration [C]∥Proceedings of the 2017 IEEE International Conference on Computer Vision(ICCV). Piscataway, NJ, USA: IEEE, 2017: 4549-4557.

LI Juncheng, FANG Faming, MEI Kangfu, et al. Multi-scale residual network for image super-resolution [C]∥Proceedings of the 2018 European Conference on Computer Vision(ECCV). Cham, Germany: Springer, 2018: 527-542.

AHN N, KANG B, SOHN K A. Fast, accurate, and lightweight super-resolution with cascading residual network [C]∥Proceedings of the 2018 European Conference on Computer Vision(ECCV). Cham, Germany: Springer, 2018: 256-272.

HE Xiangyu, MO Zitao, WANG Peisong, et al. ODE-inspired network design for single image super-resolution [C]∥Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2019: 1732-1741.

ZHAO Hang, GALLO O, FROSIO I, et al. Loss functions for image restoration with neural networks [J]. IEEE Transactions on Computational Imaging, 2017, 3(1): 47-57.

WANG Z, SIMONCELLI E P, BOVIK A C. Multiscale structural similarity for image quality assessment [C]∥Proceedings of the 37th Asilomar Conference on Signals, Systems Computers. Piscataway, NJ, USA: IEEE, 2003: 1398-1402.

BEVILACQUA M, ROUMY A, GUILLEMOT C, et al. Low-complexity single-image super-resolution based on nonnegative neighbor embedding [C]∥Proceedings of the British Machine Vision Conference. Guildford, UK: BMVA, 2012: 135.

DE SOUZA FARIA G, KIM H Y. Differential audio analysis: a new side-channel attack on PIN pads [J]. International Journal of Information Security, 2019, 18(1): 73-84.

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 8th IEEE International Conference on Computer Vision(ICCV). Piscataway, NJ, USA: IEEE, 2001: 416-423.

HUANG Jiabin, SINGH A, AHUJA N. Single image super-resolution from transformed self-exemplars [C]∥Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2015: 5197-5206.

WANG Zhou, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity [J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.

-------

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

深度学习驱动的碳纤维管壁缺陷镜面红外检测无损定量评估方法

面向模型预测控制的风电机组深度Koopman全局线性建模方法

主蒸汽管道破裂事故下蒸汽发生器的动态液位预测

融合U-net网络的纯卷积视频预测模型

一种双阻尼小波赋能的可解释卷积神经网络在轴承故障诊断中的应用