2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于多尺度特征融合反投影网络的图像超分辨率重建

孙超文 陈晓

孙超文,  陈晓.  基于多尺度特征融合反投影网络的图像超分辨率重建.  自动化学报,  2021,  47(7): 1689−1700 doi: 10.16383/j.aas.c200714
引用本文: 孙超文,  陈晓.  基于多尺度特征融合反投影网络的图像超分辨率重建.  自动化学报,  2021,  47(7): 1689−1700 doi: 10.16383/j.aas.c200714
Sun Chao-Wen,  Chen Xiao.  Multiscale feature fusion back-projection network for image super-resolution.  Acta Automatica Sinica,  2021,  47(7): 1689−1700 doi: 10.16383/j.aas.c200714
Citation: Sun Chao-Wen,  Chen Xiao.  Multiscale feature fusion back-projection network for image super-resolution.  Acta Automatica Sinica,  2021,  47(7): 1689−1700 doi: 10.16383/j.aas.c200714

基于多尺度特征融合反投影网络的图像超分辨率重建

doi: 10.16383/j.aas.c200714
基金项目: 江苏省333高层次人才培养工程项目(2625); 江苏高校优势学科建设工程资助项目资助
详细信息
    作者简介:

    孙超文:南京信息工程大学电子与信息工程学院硕士研究生. 2018年获得南京理工大学紫金学院电子工程与光电技术系学士学位. 主要研究方向为深度学习和计算机视觉. E-mail: 20181219071@nuist.edu.cn

    陈晓:南京信息工程大学电子与信息工程学院教授. 主要研究方向为现代电子系统设计, 信号与信息处理, 图像处理, 超声成像等. 本文通信作者. E-mail: chenxiao@nuist.edu.cn

Multiscale Feature Fusion Back-projection Network for Image Super-resolution

Funds: Supported by 333 High Level Personnel Training Project Jiangsu Province of China (2625); the Priority Academic Program Development of Jiangsu Higher Education Institutions
More Information
    Author Bio:

    SUN Chao-Wen Master student at the School of Electronic and Information Engineering, Nanjing University of Information Science and Technology. She received her bachelor degree in Electronic Engineering and Optoelectronic Technology from Zijin College, Nanjing University of Science and Technology in 2018. Her research interest covers deep learning and computer vision

    CHEN Xiao Professor at the School of Electronic and Information Engineering, Nanjing University of Information Science and Technology. His research interest covers modern electronic system design, signal and information processing, image processing, and ultrasonic imaging. Corresponding author of this paper

  • 摘要:

    针对现有图像超分辨率重建方法恢复图像高频细节能力较弱、特征利用率不足的问题, 提出了一种多尺度特征融合反投影网络用于图像超分辨率重建. 该网络首先在浅层特征提取层使用多尺度的卷积核提取不同维度的特征信息, 增强跨通道信息融合能力; 然后,构建多尺度反投影模块通过递归学习执行特征映射, 提升网络的早期重建能力; 最后,将局部残差反馈结合全局残差学习促进特征的传播和利用, 从而融合不同深度的特征信息进行图像重建. 对图像进行×2 ~ ×8超分辨率的实验结果表明, 本方法的重建图像质量在主观感受和客观评价指标上均优于现有图像超分辨率重建方法, 超分辨率倍数大时重建性能相比更优秀.

  • 图  1  本文算法网络结构图

    Fig.  1  The structure of the proposed network

    图  2  8倍放大下对特征提取模块卷积核大小的分析

    Fig.  2  Analysis of kernel size in the feature extraction module on ×8 enlargement

    图  3  主流重建算法在Set5数据集上对于×8 SR的平均PSNR和参数数量对比

    Fig.  3  Comparison of the average PSNR and the number of parameters of the mainstream reconstruction algorithm for ×8 SR on Set5

    图  4  Set5测试集下对不同网络的性能分析

    Fig.  4  Analysis of different networks under Set5

    图  5  在Set5上×8 SR的可视化结果(woman)

    Fig.  5  Visualized results of ×8 SR on Set5 (woman)

    图  9  在Manga109上×8 SR的可视化结果(TouyouKidan)

    Fig.  9  Visualized results of ×8 SR on Manga109 (TouyouKidan)

    图  6  在Set14上×8 SR的可视化结果(zebra)

    Fig.  6  Visualized results of ×8 SR on Set14 (zebra)

    图  7  在BSD100上×8 SR的可视化结果(210779)

    Fig.  7  Visualized results of ×8 SR on BSD100 (210779)

    图  8  在Urban100上×8 SR的可视化结果(img005)

    Fig.  8  Visualized results of ×8 SR on Urban100 (img005)

    表  1  输入块大小、参数数量和网络超参数设置

    Table  1  The settings of input patch size, number of parameters and network hyperparameters

    放大倍数× 2× 3× 4× 8
    参数数量50162116490771816193916812691
    输入块尺寸60 × 6050 × 5040 × 4020 × 20
    特征提取模块特征提取层${f_{1 \times 1}}$: Conv(128, 1, 1, 0); ${f_{{\rm{3}} \times {\rm{3}}}}$: Conv (128, 3, 1, 1); ${f_{{\rm{5}} \times {\rm{5}}}}$: Conv(128, 5, 1, 2)
    特征融合层Conv(128×3, 1, 1, 1)
    特征映射模块支路1Conv1(64, 6, 2, 2)Conv1(64, 7, 3, 2)Conv1(64, 8, 4, 2)Conv1(64, 12, 8, 2)
    支路2Conv2(64, 8, 2, 3)Conv2(64, 9, 3, 3)Conv2(64, 10, 4, 3)Conv2(64, 14, 8, 3)
    重建模块Conv(64×7, 3, 1, 1)
    递归次数7
    深度73
    注: Conv(C, K, S, P): C表示通道数, K表示卷积核大小, S表示步长, P表示填充.
    下载: 导出CSV

    表  2  对特征提取模块卷积核大小的分析

    Table  2  Analysis of the kernel size of the feature extraction module

    ScaleMethodSet5 PSNR/SSIMSet14 PSNR/SSIMBSD100 PSNR/SSIMUrban100 PSNR/SSIMManga109 PSNR/SSIM
    ×8Ours_13527.13/0.781925.02/0.644524.86/0.599222.59/0.623124.85/0.7885
    Ours_35727.09/0.780625.03/0.643724.86/0.598622.57/0.621924.78/0.7859
    下载: 导出CSV

    表  3  对多尺度投影单元的卷积核大小分析

    Table  3  Analysis of the kernel size of the multi-scale projection unit

    Scale(卷积核尺寸、步长、填充)PSNR (dB)
    支路1支路2Set5Set14BSD100Urban100Manga109
    ×8(8, 8, 0)(10, 8, 1)27.0024.9524.8222.4524.68
    (10, 8, 1)(12, 8, 2)27.0824.9924.8422.5324.77
    (12, 8, 2)(14, 8, 3)27.1325.0224.8622.5924.85
    下载: 导出CSV

    表  4  ×8模型在Set5和Set14测试集上的深度分析

    Table  4  The depth analysis of the ×8 model on Set5 and Set14 datasets

    递归次数网络层数参数数量PSNR (dB)
    Set5Set14
    1131680232326.5024.53
    3331680577926.9824.89
    4431680750727.0324.94
    5531680923527.0524.96
    6631681096327.0724.98
    7731681269127.1325.02
    8831681441927.1325.02
    下载: 导出CSV

    表  5  不同SR算法在×2、×3和×4上的定量评估

    Table  5  Quantitative comparison of different algorithms on ×2, ×3, and ×4

    ScaleMethodSet5 PSNR/SSIMSet14 PSNR/SSIMBSD100 PSNR/SSIMUrban100 PSNR/SSIMManga109 PSNR/SSIM
    × 21. Bicubic33.68/0.930430.24/0.869129.56/0.843526.88/0.840531.05/0.9350
    × 22. SRCNN36.66/0.954232.45/0.906731.36/0.887929.51/0.894635.72/0.9680
    × 23. ESPCN37.00/0.955932.75/0.909831.51/0.893929.87/0.906536.21/0.9694
    × 24. FSRCNN37.06/0.955432.76/0.907831.53/0.891229.88/0.902429.88/0.9024
    × 25. VDSR37.53/0.958733.05/0.912731.90/0.896030.77/0.914137.16/0.9740
    × 26. DRCN37.63/0.958833.06/0.912131.85/0.894230.76/0.913337.57/0.9730
    × 27. LapSRN37.52/0.959132.99/0.912431.80/0.894930.41/0.910137.53/0.9740
    × 28. DRRN37.74/0.959133.23/0.913632.05/0.897331.23/0.918837.92/0.9760
    × 29. DBPN-R64-737.57/0.958933.09/0.913231.83/0.895130.75/0.913337.65/0.9747
    × 210. IDN37.83/0.960033.30/0.914832.08/0.898531.27/0.919638.02/0.9749
    × 211. SRMDNF37.79/0.960133.32/0.915932.05/0.898531.33/0.920438.07/0.9761
    × 212. DRFN37.71/0.959533.29/0.914232.02/0.897931.08/0.917933.42/0.9123
    × 213. MRFN37.98/0.961133.41/0.915932.14/0.899731.45/0.922138.29/0.9759
    × 2Ours37.82/0.959933.35/0.915632.04/0.898031.49/0.921838.23/0.9762
    × 31. Bicubic30.40/0.868627.54/0.774127.21/0.738924.46/0.734926.95/0.8560
    × 32. SRCNN32.75/0.909029.29/0.821528.41/0.786326.24/0.799130.48/0.9120
    × 33. ESPCN33.02/0.913529.49/0.827128.50/0.793726.41/0.816130.79/0.9181
    × 34. FSRCNN33.20/0.914929.54/0.827728.55/0.794526.48/0.817530.98/0.9212
    × 35. VDSR33.66/0.921329.78/0.831828.83/0.797627.14/0.827932.01/0.9340
    × 36. DRCN33.82/0.922629.77/0.831428.80/0.796327.15/0.827732.31/0.9360
    × 37. LapSRN33.82/0.922729.79/0.832028.82/0.797327.07/0.827132.21/0.9350
    × 38. DRRN34.03/0.924429.96/0.834928.95/0.800427.53/0.837732.74/0.9390
    × 39. DBPN-R64-733.90/0.923629.99/0.835328.87/0.799127.35/0.833632.59/0.9373
    × 310. IDN34.11/0.925329.99/0.835428.95/0.801327.42/0.835932.69/0.9378
    × 311. SRMDNF34.12/0.925430.04/0.838228.97/0.802527.57/0.839833.00/0.9403
    × 312. DRFN34.01/0.923430.06/0.836628.93/0.801027.43/0.835930.59/0.8539
    × 313. MRFN34.21/0.926730.03/0.836328.99/0.802927.53/0.838932.82/0.9396
    × 3Ours34.31/0.926530.29/0.840829.05/0.803527.94/0.847233.37/0.9433
    × 41. Bicubic28.43/0.810926.00/0.702325.96/0.667823.14/0.657425.15/0.7890
    × 42. SRCNN30.48/0.862827.50/0.751326.9/0.710324.52/0.722627.66/0.8580
    × 43. ESPCN30.66/0.864627.71/0.756226.98/0.712424.60/0.736027.70/0.8560
    × 44. FSRCNN30.73/0.860127.71/0.748826.98/0.702924.62/0.727227.90/0.8517
    × 45. VDSR31.35/0.883828.02/0.767827.29/0.725225.18/0.752528.82/0.8860
    × 46. DRCN31.53/0.885428.03/0.767327.24/0.723325.14/0.751128.97/0.8860
    × 47. LapSRN31.54/0.886628.09/0.769427.32/0.726425.21/0.755329.09/0.8900
    × 48. DRRN31.68/0.888828.21/0.772027.38/0.728425.44/0.763829.46/0.8960
    × 49. DBPN-R64-731.92/0.891528.41/0.777027.42/0.730425.59/0.768129.92/0.9003
    × 410. IDN31.82/0.890328.25/0.773027.41/0.729725.41/0.7632
    × 411. SRMDNF31.96/0.892528.35/0.778727.49/0.733725.68/0.773130.09/0.9024
    × 412. DRFN31.55/0.886128.30/0.773727.39/0.729325.45/0.762928.99/0.8106
    × 413. MRFN31.90/0.891628.31/0.774627.43/0.730925.46/0.765429.57/0.8962
    × 4Ours32.31/0.896328.71/0.784327.66/0.738326.30/0.792230.84/0.9126
    下载: 导出CSV

    表  6  不同SR算法在×8上的定量评估

    Table  6  Quantitative comparison of different algorithms on ×8

    ScaleMethodSet5 PSNR/SSIMSet14 PSNR/SSIMBSD100 PSNR/SSIMUrban100 PSNR/SSIMManga109 PSNR/SSIM
    × 81. Bicubic24.40/0.658023.10/0.566023.67/0.548020.74/0.516021.47/0.6500
    × 82. SRCNN25.33/0.690023.76/0.591024.13/0.566021.29/0.544022.46/0.6950
    × 83. ESPCN25.75/0.673824.21/0.510924.37/0.527721.59/0.542022.83/0.6715
    × 84. FSRCNN25.42/0.644023.94/0.548224.21/0.511221.32/0.509022.39/0.6357
    × 85. VDSR25.93/0.724024.26/0.614024.49/0.583021.70/0.571023.16/0.7250
    × 86. LapSRN26.15/0.738024.35/0.620024.54/0.586021.81/0.581023.39/0.7350
    × 87. DRFN26.22/0.740024.57/0.625024.60/0.5870
    × 88. MSRN26.59/0.725424.88/0.596124.70/0.541022.37/0.597724.28/0.7517
    × 89. DBPN-R64-726.82/0.770024.77/0.634624.72/0.592822.22/0.603324.19/0.7664
    × 810. EDSR26.96/0.776224.91/0.642024.81/0.598522.51/0.622124.69/0.7841
    × 8Ours27.13/0.781925.02/0.644524.86/0.599222.59/0.623124.85/0.7885
    下载: 导出CSV
  • [1] 张宁, 王永成, 张欣, 徐东东. 基于深度学习的单幅图片超分辨率重构研究进展. 自动化学报, 2020, 46(12): 2479−2499

    Zhang Ning, Wang Yong-Cheng, Zhang Xin, Xu Dong-Dong. A review of single image super-resolution based on deep learning. Acta Automatica Sinica, 2020, 46(12): 2479−2499
    [2] 张毅锋, 刘袁, 蒋程, 程旭. 用于超分辨率重建的深度网络递进学习方法. 自动化学报, 2020, 46(2): 274−282

    Zhang Yi-Feng, Liu Yuan, Jiang Cheng, Cheng Xu. A curriculum learning approach for single image super resolution. Acta Automatica Sinica, 2020, 46(2): 274−282
    [3] Tan Y, Cai J, Zhang S, Zhong W, Ye L. Image compression algorithms based on super-resolution reconstruction technology. In: Proceedings of the 2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC), 2019. 162−166
    [4] You C, Li G, Zhang Y Zhang, X, Shan H, Li M, Ju S, Zhao Z, Zhang Z, Cong W, Vannier M W, Saha P K, Hoffman E A, Wang G. CT super-resolution GAN constrained by the identical, residual, and cycle learning ensemble (GAN-CIRCLE). IEEE Transactions on Medical Imaging, 2020, 39(1): 188−203 doi: 10.1109/TMI.2019.2922960
    [5] Pang Y, Cao J, Wang J, Han J. JCS-Net: Joint classification and super-resolution network for small-scale pedestrian detection in surveillance images. IEEE Transactions on Information Forensics and Security, 2019, 14(12): 3322−3331 doi: 10.1109/TIFS.2019.2916592
    [6] 周登文, 赵丽娟, 段然, 柴晓亮. 基于递归残差网络的图像超分辨率重建. 自动化学报, 2019, 45(6): 1157−1165

    Zhou Deng-Wen, Zhao Li-Juan, Duan Ran, Chai Xiao-Liang. Image super-resolution based on recursive residual networks. Acta Automatica Sinica, 2019, 45(6): 1157−1165
    [7] 孙旭, 李晓光, 李嘉锋, 卓力. 基于深度学习的图像超分辨率复原研究进展. 自动化学报, 2017, 43(5): 697−709

    Sun Xu, Li Xiao-Guang, Li Jia-Feng, Zhuo Li. Review on deep learning based image super-resolution restoration algorithms. Acta Automatica Sinica, 2017, 43(5): 697−709
    [8] Dong C, Loy C C, He K, Tang X. Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295−307 doi: 10.1109/TPAMI.2015.2439281
    [9] Dong C, Loy C C, He K, Tang X. Learning a deep convolutional network for image super-resolution. In: Proceedings of the 2014 European Conference on Computer Vision (ICCV), Springer, Cham, 2014. 184−199
    [10] 刘建伟, 赵会丹, 罗雄麟, 许鋆. 深度学习批归一化及其相关算法研究进展. 自动化学报, 2020, 46(6): 1090−1120

    Liu Jian-Wei, Zhao Hui-Dan, Luo Xiong-Lin, Xu Jun. Research progress on batch normalization of deep learning and its related algorithms. Acta Automatica Sinica, 2020, 46(6): 1090−1120
    [11] Kim J, Kwon Lee J, Mu Lee K. Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016. 1646–1654
    [12] B. Lim, S. Son, H. Kim, S. Nah, and K. M. Lee. Enhanced deep residual networks for single image super-resolution. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, 2017. 136–144
    [13] K. He, X. Zhang, S. Ren and J. Sun. Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, 770−778
    [14] Tong T, Li G, Liu X, Gao Q. Image super-resolution using dense skip connections. In: Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 2017. 4809−4817
    [15] Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y. Residual dense network for image super-resolution. In: Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018. 2472−2481
    [16] Haris M, Shakhnarovich G, Ukita N. Deep back-projection networks for single image super-resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2020.3002836, 2020.
    [17] Huang G, Liu Z, Van Der Maaten L, Weinberger K Q, Densely connected convolutional networks. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017. 2261−2269
    [18] Kim J, Lee J K, Lee K M. Deeply-recursive convolutional network for image super-resolution. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016. 1637−1645
    [19] Tai Y, Yang J, Liu X. Image super-resolution via deep recursive residual network. In: Proceeding of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017. 2790−2798
    [20] Dong C, Loy C C, Tang X. Accelerating the super-resolution convolutional neural network. In: Proceedings of the European Conference on Computer Vision, Springer, Cham, 2016. 391–407
    [21] Shi W, Caballero J, Huszár F, Totz J, Aitken A P, Bishop R, Rueckert D, Wang Z. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016. 1874−1883
    [22] Li Jun-Cheng, Fang Fa-Ming, Mei Kang-Fu, Zhang Gui-Xu. Multiscale residual network for image super-resolution. In: Proceedings of the European Conference on Computer Vision, Springer, Cham, 2018. 527−542
    [23] Lai W, Huang J, Ahuja N, Yang M. Deep Laplacian pyramid networks for fast and accurate super-resolution. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017. 5835−5843
    [24] Agustsson E, Timofte R. NTIRE 2017 challenge on single image super-resolution: Dataset and study. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, 2017. 1122−1131
    [25] Deng J, Dong W, Socher R, Li L, Li Kai and Li Fei-Fei. ImageNet: A large-scale hierarchical image database. In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 2009. 248−255
    [26] Szegedy C, Liu Wei, Jia Yang-Qing, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015. 1−9
    [27] Bevilacqua M, Roumy A, Guillemot C, Alberi-Morel M L, Low-complexity single image super-resolution based on nonnegative neighbor embedding. In: Proceedings of the British Machine Vision Conference, 2012. 1–10
    [28] Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations. In: Proceedings of the International Conference on Curves and Surfaces, Springer, Berlin, Heidelberg, 2010. 711–730
    [29] Arbeláez P, Maire M, Fowlkes C, Malik J. Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5): 898−916 doi: 10.1109/TPAMI.2010.161
    [30] Huang J, Singh A, Ahuja N. Single image super-resolution from transformed self-exemplars. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015. 5197−5206
    [31] Matsui Y, Ito K, Aramaki Y, Fujimoto A, Ogawa T, Yamasaki T, Aizawa K. Sketch-based manga retrieval using Manga109 dataset. Multimedia Tools & Applications, 2017, 76(20): 21811−21838
    [32] Zhou Wang, Bovik A C, Sheikh H R, Simoncelli E P. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 2004, 13(4): 600−612
    [33] He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015. 1026−1034
    [34] Kingma D P, Ba J. Adam: A method for stochastic optimization, arXiv preprint, arXiv: 1412.6980, 2014.
    [35] 毕敏敏. 基于深度学习的图像超分辨率技术研究[硕士学位论文]. 哈尔滨工业大学, 中国, 2020.

    Bi Min-Min. Research on image super-resolution technology based on deep learning [Master thesis]. Harbin Institute of Technology, China, 2020.
    [36] 李彬, 喻夏琼, 王平, 傅瑞罡, 张虹. 基于深度学习的单幅图像超分辨率重建综述. 计算机工程与科学, 2021, 43(01): 112−124

    Li Bin, Yu Xia-Qiong, Wang Ping, Fu Rui-Gang, Zhang Hong. A survey of single image super-resolution reconstruction based on deep learning. Computer Engineering and Science, 2021, 43(01): 112−124
    [37] Yang X, Mei H, Zhang J, Xu K, Yin B, Zhang Q, Wei X. DRFN: Deep recurrent fusion network for single-image super-resolution with large factors. IEEE Transactions on Multimedia, 2019, 21(2): 328−337 doi: 10.1109/TMM.2018.2863602
    [38] Hui Z, Wang X, Gao X. Fast and accurate single image super-resolution via information distillation network. In: Proceeding of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018.723−731
    [39] Zhang K, Zuo W, Zhang L. Learning a single convolutional super-resolution network for multiple degradations. In: Proceeding of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018. 3262−3271
    [40] He Z, Cao Y, Du L, Xu B, Yang J, Cao Y, Tang S, Zhuang Y. MRFN: Multi-receptive-field network for fast and accurate single image super-resolution. IEEE Transactions on Multimedia, 2020, 22(4): 1042−1054 doi: 10.1109/TMM.2019.2937688
  • 加载中
图(9) / 表(6)
计量
  • 文章访问数:  1236
  • HTML全文浏览量:  417
  • PDF下载量:  262
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-09-02
  • 录用日期:  2021-02-09
  • 网络出版日期:  2021-03-17
  • 刊出日期:  2021-07-27

目录

    /

    返回文章
    返回