2.624

2020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

基于组-信息蒸馏残差网络的轻量级图像超分辨率重建

王云涛 赵蔺 刘李漫 陶文兵

王云涛, 赵蔺, 刘李漫, 陶文兵. 基于组-信息蒸馏残差网络的轻量级图像超分辨率重建. 自动化学报, 2022, 48(x): 1−16 doi: 10.16383/j.aas.c211089
引用本文: 王云涛, 赵蔺, 刘李漫, 陶文兵. 基于组-信息蒸馏残差网络的轻量级图像超分辨率重建. 自动化学报, 2022, 48(x): 1−16 doi: 10.16383/j.aas.c211089
Wang Yun-Tao, Zhao Lin, Liu Li-Man, Tao Wen-Bing. G-idrn: an group-information distillation residual network for lightweight image super-resolution. Acta Automatica Sinica, 2022, 48(x): 1−16 doi: 10.16383/j.aas.c211089
Citation: Wang Yun-Tao, Zhao Lin, Liu Li-Man, Tao Wen-Bing. G-idrn: an group-information distillation residual network for lightweight image super-resolution. Acta Automatica Sinica, 2022, 48(x): 1−16 doi: 10.16383/j.aas.c211089

基于组-信息蒸馏残差网络的轻量级图像超分辨率重建

doi: 10.16383/j.aas.c211089
基金项目: 国家自然科学基金(61976227, 62176096), 湖北省国家自然科学基金(2019CFB622)资助
详细信息
    作者简介:

    王云涛:中南民族大学生物医学工程学院硕士研究生. 主要研究方向为图像处理, 深度学习和图像超分辨率. E-mail: ytao-wang@scuec.edu.cn

    赵蔺:华中科技大学人工智能与自动化学院博士研究生. 主要研究方向为图像识别, 图像超分辨率和点云实例语义分割. E-mail: linzhao@hust.edu.cn

    刘李漫:中南民族大学生物医学工程学院副教授. 主要研究方向为图像处理, 深度学习和计算机视觉. 本文通信作者. E-mail: limanliu@mail.scuec.edu.cn

    陶文兵:华中科技大学人工智能与自动化学院教授. 主要研究方向为图像分割, 目标识别和3D重建. E-mail: wenbingtao@hust.edu.cn

G-IDRN: An Group-information Distillation Residual Network for Lightweight Image Super-resolution

Funds: Supported by National Natural Science Foundation of China (61976227, 62176096) and National Natural Science Foundation of Hubei Province (2019CFB622)
More Information
    Author Bio:

    WANG Yun-Tao Master student at the School of Biomedical Engineering, South-central Minzu University. His research interest covers image processing, deep learning and image super-resolution

    ZHAO Lin Ph.D. candidate at the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology. His research interest covers image recognition, image super-resolution, and point cloud instance semantic segmentation

    LIU Li-Man Associate professor at the School of Biomedical Engineering, South-central Minzu University. Her research interest covers image processing, deep learning and computer vision. Corresponding author of this paper

    TAO Wen-Bing Professor at the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology. His research interest covers image segmentation, target recognition and 3D reconstruction

  • 摘要: 目前, 基于深度学习的超分辨算法已经取得了很好的性能. 但是这些方法通常具有较大的内存消耗和较高的计算复杂度, 很难应用到低算力或便携式设备上. 为了解决这一问题, 设计了一种轻量级的组-信息蒸馏残差网络用于快速且精确的单图像超分辨率. 具体来说, 提出一个更加有效的组-信息蒸馏模块, 作为网络特征提取基本块. 同时, 引入密集快捷连接对多个基本块进行组合, 构建组-信息蒸馏残差组, 捕获多层级信息和有效重利用特征. 另外, 还提出一个轻量的非对称残差Non-local模块对长距离依赖关系进行建模, 进一步提升超分的性能. 最后, 设计一个高频损失函数去解决像素损失带来图片细节平滑的问题. 大量的实验证明了该算法相较于其他先进方法, 可以在图像超分辨率性能和模型复杂度之间取得更好的平衡, 其在公开测试数据集B100上4倍超分速率达到56FPS, 比残差注意力网络快15倍.
  • 图  1  Urban100数据集($ \times 2$)上参数数量和峰值信噪比的对比结果

    Fig.  1  Comparison results of the number of parameters and the peak single-to-noise ratio. The comparison is conducted on Urban100 with the $ \times 2$ scale factor

    图  2  不同SR方法对Urban100数据集中图像“img024”超分的重建结果($ \times 4$)

    Fig.  2  The reconstruction results of various SR methods on img024 from Urban100 ($ \times 4$)

    图  3  组-信息蒸馏残差网络(G-IDRN)整体架构

    Fig.  3  The architecture of the group-information distillation residual network (G-IDRN)

    图  4  G-IDB对RFDB的改进图

    Fig.  4  G-IDB is an improvement of RFDB

    图  5  非对称残差Non-Local模块

    Fig.  5  The asymmetric Non-local residual block

    图  6  “barbara.png”(Set14 $ \times 3$)的高频提取图

    Fig.  6  High-frequency extraction image of barbara.png (Set14 $ \times 3$)

    图  7  HR图像和对应使用低频滤波器提取的低频信息图

    Fig.  7  HR images and their low-frequency information images extracted by low-pass filter

    图  8  不同损失权重的PSNR分数差值对比结果

    Fig.  8  Comparison results of PSNR scores differences for various loss weight

    图  9  PSNR/SSIM的差值图

    Fig.  9  Differential results of PSNR/SIMM scores

    图  10  在Urban100数据集($ \times 4$)上先进算法与所提G-IDRN的定性结果对比

    Fig.  10  Visual qualitative comparisons of the state-of-the-art lightweight methods and our G-IDRN on Urban100 dataset for $ \times 4$ SR

    图  11  在真实图像上的可视化对比结果

    Fig.  11  Visual comparison on a real-world image

    图  12  在Urban100数据集($ \times 4$)上SSIM与模型参数数量的对比

    Fig.  12  Comparison results of SSIM and the number of parameters. The comparison is conducted on Urban100 with the $ \times 4$ scale factor

    表  1  消融实验结果

    Table  1  Ablation experiment results

    基本块双路重建策略DS连接ANRBSet5 PSNR (dB)参数量 (K)增幅PSNR (dB) | 参数量 (K)
    RFDB37.893534.00 | 0
    $ \checkmark$37.931514.2$ \uparrow$ 0.038 | $ \downarrow$ 19.8
    $ \checkmark$37.891520.2$ \downarrow$ 0.002 | $ \downarrow$ 13.8
    $ \checkmark$37.916534.3$ \uparrow$ 0.023 | $ \uparrow$ 0.3
    $ \checkmark$$ \checkmark$37.934514.4$ \uparrow$ 0.041 | $ \downarrow$ 19.6
    $ \checkmark$$ \checkmark$$ \checkmark$37.940500.5$ \uparrow$ 0.047 | $ \downarrow$ 33.5
    GIDB37.955449.4$ \uparrow$ 0.062 | $ \downarrow$ 84.6
    $ \checkmark$$ \checkmark$$ \checkmark$37.965383.2$ \uparrow$ 0.072 | $ \downarrow$ 150.8
    下载: 导出CSV

    表  2  ANRB中不同采样特征点数的实验结果

    Table  2  The experimental results for different sampled feature points in ANRB

    特征点数Set5 PSNR (dB)Manga109
    PSNR (dB)
    $128\times 128$
    内存 (M)
    $180\times 180$
    内存 (M)
    无ANRB37.88838.396216419
    $S=50$37.89338.439224436
    $S=110$37.89538.443232452
    $S=222$37.86138.325246480
    $S=\infty$37.883内存溢出2 2668 431
    下载: 导出CSV

    表  3  使用不同损失权重结果对比 (PSNR (dB))

    Table  3  Comparison of results with different loss weights (PSNR (dB))

    不同权重系数Set5Set14B100Urban100Manga109
    $\alpha =1.0$, $\beta =0$37.90733.42332.06331.83038.483
    $\alpha =0.8$, $\beta =0.2$37.90033.40632.07131.85038.476
    $\alpha =0.6$, $\beta =0.4$37.93033.42132.07531.84338.483
    $\alpha =0.4$, $\beta =0.6$37.97533.44432.08431.87838.576
    $\alpha =0.2$, $\beta =0.8$37.90133.46732.08431.86038.462
    下载: 导出CSV

    表  4  对于$\times 2$$\times 3$$\times 4$尺度, 各种算法在5个基准数据集上的定量对比结果 (PSNR (dB) / SSIM))

    Table  4  Quantitative comparisons of various algorithms for scale factor $\times 2$, $\times 3$ and $\times 4$ on the five benchmark datasets (PSNR (dB) / SSIM)

    方法尺度参数量 (K)Set5 PSNR / SSIMSet14 PSNR / SSIMB100 PSNR / SSIMUban100 PSNR / SSIMManga109 PSNR / SSIM
    Bicubic$\times 2$33.66 / 0.929930.24 / 0.868829.56 / 0.843126.88 / 0.840330.80 / 0.9339
    SRCNN[15] 836.66 / 0.954232.45 / 0.906731.36 / 0.887929.50 / 0.894635.60 / 0.9663
    DRCN[18] 1 77437.63 / 0.958833.04 / 0.911831.85 / 0.894230.75 / 0.913337.55 / 0.9732
    LapSRN[56] 25137.52 / 0.959132.99 / 0.912431.80 / 0.895230.41 / 0.910337.27 / 0.9740
    DRRN[57] 29837.74 / 0.959133.23 / 0.913632.05 / 0.897331.23 / 0.918837.88 / 0.9749
    MemNet[26] 67837.78 / 0.959733.28 / 0.914232.08 / 0.897831.31 / 0.919537.72 / 0.9740
    IDN[22] 55337.83 / 0.960033.30 / 0.914832.08 / 0.898531.27 / 0.919638.01 / 0.9749
    SRMDNF[58] 1 51137.79 / 0.960133.32 / 0.915932.05 / 0.898531.33 / 0.920438.07 / 0.9761
    CARN[21] 1 59237.76 / 0.959033.52 / 0.916632.09 / 0.897831.92 / 0.925638.36 / 0.9765
    SMSR[59] 98538.00 / 0.960133.64 / 0.917932.17 / 0.899332.19 / 0.928438.76 / 0.9771
    IMDN[11] 69438.00 / 0.960533.63 / 0.917732.19 / 0.899732.17 / 0.928238.88 / 0.9774
    IMDN[60] 69437.94 / 0.960433.56 / 0.917232.14 / 0.899232.03 / 0.9270− / −
    IMDN-JDSR[60] 69438.03 / 0.960533.57 / 0.917632.16 / 0.899532.09 / 0.9271− / −
    PAN[61] 26138.00 / 0.960533.59 / 0.918132.18 / 0.899732.01 / 0.927338.70 / 0.9773
    RFDN-L[12] 62638.03 / 0.960633.65 / 0.918332.18 / 0.899732.16 / 0.928238.88 / 0.9772
    LatticeNet[31] 75938.03 / 0.960733.70 / 0.918732.20 / 0.899932.25 / 0.9288− / −
    G-IDRN 55438.09 / 0.960833.80 / 0.920332.42 / 0.900332.42 / 0.931138.96 / 0.9773
    Bicubic$\times 3$30.39 / 0.868227.55 / 0.774227.21 / 0.738524.46 / 0.734926.95 / 0.8556
    SRCNN[15] 832.75 / 0.909029.30 / 0.821528.41 / 0.786326.24 / 0.798930.48 / 0.9117
    DRCN[18] 1 77433.82 / 0.922629.76 / 0.831128.80 / 0.796327.15 / 0.827632.24 / 0.9343
    LapSRN[56] 50233.81 / 0.922029.79 / 0.832528.82 / 0.798027.07 / 0.827532.21 / 0.9350
    DRRN[57] 29834.03 / 0.924429.96 / 0.834928.95 / 0.800427.53 / 0.837832.71 / 0.9379
    MemNet[26] 67834.09 / 0.924830.00 / 0.835028.96 / 0.800127.56 / 0.837632.51 / 0.9369
    IDN[22] 55334.11 / 0.925329.99 / 0.835428.95 / 0.801327.42 / 0.835932.71 / 0.9381
    SRMDNF[58] 1 52834.12 / 0.925430.04 / 0.838228.97 / 0.802527.57 / 0.839833.00 / 0.9403
    CARN[21] 1 59234.29 / 0.925530.29 / 0.840729.06 / 0.803428.06 / 0.849333.50 / 0.9440
    SMSR[59] 99334.40 / 0.927030.33 / 0.841229.10 / 0.805028.25 / 0.853633.68 / 0.9445
    IMDN[11] 70334.36 / 0.927030.32 / 0.841729.09 / 0.804728.16 / 0.851933.61 / 0.9445
    IMDN[60] 70334.33 / 0.926630.30 / 0.840929.05 / 0.803728.07 / 0.8496− / −
    IMDN-JDSR[60] 70334.36 / 0.926930.32 / 0.841329.08 / 0.804528.12 / 0.8498− / −
    PAN[61] 26134.40 / 0.927130.36 / 0.842329.11 / 0.805028.11 / 0.851133.61 / 0.9448
    RFDN-L[12] 63334.39 / 0.927130.35 / 0.841929.11 / 0.805428.24 / 0.853433.74 / 0.9453
    LatticeNet[31] 76534.40 / 0.927230.32 / 0.841629.10 / 0.804928.19 / 0.8513− / −
    G-IDRN 56534.43 / 0.927730.41 / 0.843129.14 / 0.806128.32 / 0.855233.79 / 0.9456
    Bicubic$\times 4$28.42 / 0.810426.00 / 0.702725.96 / 0.667523.14 / 0.657724.89 / 0.7866
    SRCNN[15] 830.48 / 0.862627.50 / 0.751326.90 / 0.710124.52 / 0.722127.58 / 0.8555
    DRCN[18] 1 77431.53 / 0.885428.02 / 0.767027.23 / 0.723325.14 / 0.751028.93 / 0.8854
    LapSRN[56] 50231.54 / 0.885228.09 / 0.770027.32 / 0.727525.21 / 0.756229.09 / 0.8900
    DRRN[57] 29831.68 / 0.888828.21 / 0.772027.38 / 0.728425.44 / 0.763829.45 / 0.8946
    MemNet[26] 67831.74 / 0.889328.26 / 0.772327.40 / 0.728125.50 / 0.763029.42 / 0.8942
    IDN[22] 55331.82 / 0.890328.25 / 0.773027.41 / 0.729725.41 / 0.763229.41 / 0.8942
    SRMDNF[58] 1 55231.96 / 0.892528.35 / 0.778727.49 / 0.733725.68 / 0.773130.09 / 0.9024
    CARN[21] 1 59232.13 / 0.893728.60 / 0.780627.58 / 0.734926.07 / 0.783730.47 / 0.9084
    SMSR[59] 1 00632.13 / 0.893728.60 / 0.780627.58 / 0.734926.11 / 0.786830.54 / 0.9084
    IMDN[11] 71532.21 / 0.894828.58 / 0.781127.56 / 0.735426.04 / 0.783830.45 / 0.9075
    IMDN[60] 71532.15 / 0.893828.56 / 0.780827.53 / 0.734526.00 / 0.7822− / −
    IMDN-JDSR[60] 71532.17 / 0.894228.62 / 0.781427.55 / 0.735026.06 / 0.7820− / −
    PAN[61] 27232.13 / 0.894828.61 / 0.782227.59 / 0.736326.11 / 0.785430.51 / 0.9095
    RFDN-L[12] 64332.23 / 0.895328.59 / 0.781427.57 / 0.736326.14 / 0.787130.61 / 0.9095
    LatticeNet[31] 77732.18 / 0.894328.61 / 0.781227.57 / 0.735526.14 / 0.7844− / −
    G-IDRN 58032.24 / 0.895828.64 / 0.782427.61 / 0.737826.24 / 0.790330.63 / 0.9096
    下载: 导出CSV

    表  5  Set14数据集 ($\times 4$) 上计算量和PSNR/SSIM的对比

    Table  5  Comparison results of FLOPs and PSNR/SSIM on Set14 ($\times 4$)

    指标CARN[21]IMDN[11]RFDN-L[12]G-IDRN
    SSIM0.78060.78100.78140.7826
    PSNR (dB)28.6028.5828.5928.64
    FLOPs (G)103.5846.6041.5436.19
    下载: 导出CSV

    表  6  在B100数据集 ($\times 4$) 上的平均运行时间

    Table  6  Average running time on B100 ($\times 4$)

    方法PSNR (dB) / SSIM参数量 (K)训练时间 (s)推理时间 (s)
    EDSR27.71/0.742043 0900.2178
    RCAN27.77/0.743615 5920.2596
    IMDN27.56/0.73547155.40.0217
    RFDN-L27.57/0.73636336.10.0250
    G-IDRN27.61/0.737858012.70.0177
    IDRN27.64/0.73892 0478.50.0692
    下载: 导出CSV
  • [1] Isaac J S, Kulkarni R. Super resolution techniques for medical image processing. In: Proceedings of the 2015 International Conference on Technologies for Sustainable Development (ICTSD). Mumbai, India: IEEE, 2015. 1−6
    [2] Rasti P, Uiboupin T, Escalera S. Anbarjafari G. Convolutional neural network super resolution for face recognition in surveillance monitoring. In: Proceedings of the International Conference on Articulated Motion and Deformable Objects. Cham, Netherlands: Springer, 2016. 175−184
    [3] Sajjadi M S M, Scholkopf B, Hirsch M. Enhancenet: Single image super-resolution through automated texture synthesis. In: Proceedings of the 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017. 4491−4500
    [4] 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). Xiamen, China: IEEE, 2019. 162-166
    [5] Luo Y, Zhou L, Wang S, Wang Z. Video satellite imagery super resolution via convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 2017, 14(12): 2398-2402 doi: 10.1109/LGRS.2017.2766204
    [6] 杨欣, 周大可, 费树岷. 基于自适应双边全变差的图像超分辨率重建. 计算机研究与发展, 2012, 49(12): 2696

    Yang Xin, Zhou Da-Ke, Fei Shu-Min. A self-adapting bilateral total aariation technology for image super-resolution reconstruction. Journal of Computer Research and Development, 2012, 49(12): 2696
    [7] Zhang L, Wu X. An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Transactions on Image Processing, 2006, 15(8): 2226-2238 doi: 10.1109/TIP.2006.877407
    [8] 潘宗序, 禹晶, 胡少兴, 孙卫东. 基于多尺度结构自相似性的单幅图像超分辨率算法. 自动化学报, 2014, 40(4): 594-603

    Pan Zong-Xu, Yu Jing, Hu Shao-Xing, Sun Wei-Dong. Single image super resolution based on multi-scale structural self-similarity. Acta Automatica Sinica, 2014, 40(4): 594-603
    [9] 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, 40(2): 274-282

    Zhang Yi-Feng, Liu Yuan, Jiang Cheng, Cheng Xu. A curriculum learning approach for single image superresolution. Acta Automatica Sinica, 2020, 46(2): 274-282
    [10] Dai T, Cai J, Zhang Y, Xia S T, Zhang L. Second-order attention network for single image super-resolution. In: Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019. 11065−11074
    [11] Hui Z, Gao X, Yang Y, Wang X. Lightweight image super-resolution with information multi-distillation network. In: Proceedings of the 27th ACM International Conference on Multimedia. New York, USA: Association for Computing Machinery, 2019. 2024−2032
    [12] Liu J, Tang J, Wu G. Residual feature distillation network for lightweight image super-resolution. In: Proceedings of the 20th European Conference on Computer Vision. Cham, Netherlands: Springer, 2020. 41−55
    [13] 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

    Sun Chao-Wen, Chen Xiao. Multiscale feature fusion back-projection network for image super-resolution. Acta Automatica Sinica, 2021, 47(7): 1689-1700
    [14] 孙玉宝, 费选, 韦志辉, 肖亮. 基于前向后向算子分裂的稀疏性正则化图像超分辨率算法. 自动化学报, 2010, 36(9): 1232-1238 doi: 10.3724/SP.J.1004.2010.01232

    Sun Yu-Bao, Fei Xuan, Wei Zhi-Hui, Xiao Liang. Sparsity regularized image super-resolution model via forward-backward operator splitting method. Acta Automatica Sinica, 2010, 36(9): 1232-1238 doi: 10.3724/SP.J.1004.2010.01232
    [15] Dong C, Loy C C, He K, Tang X. Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38(2): 295-307
    [16] Dong C, Loy C C, Tang X. Accelerating the super-resolution convolutional neural network. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE, 2016. 391−407
    [17] Kim J, Lee J K, Lee K M. Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE, 2016. 1646−1654
    [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. Las Vegas, USA: IEEE, 2016. 1637−1645
    [19] Lim B, Son S, Kim H, Nah S, Mu Lee K. Enhanced deep residual networks for single image super-resolution. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu, USA: IEEE, 2017. 136−144
    [20] Zhang Y, Li K, Li K, Wang L, Zhong B, Fu Y. Image super-resolution using very deep residual channel attention networks. In: Proceedings of the 18th European Conference on Computer Vision. Mohini, Germany: Springer, 2018. 286−301
    [21] Ahn N, Kang B, Sohn K A. Fast, accurate, and lightweight super-resolution with cascading residual network. In: Proceedings of the 18th European Conference on Computer Vision. Mohini, Germany: Springer, 2018: 252−268
    [22] Hui Z, Wang X, Gao X. Fast and accurate single image super-resolution via information distillation network. In: Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018. 723−731
    [23] Zhu Z, Xu M, Bai S, Huang T, Bai X. Asymmetric non-local neural networks for semantic segmentation. In: Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019. 593−602
    [24] Huang J B, 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. Boston, USA: IEEE, 2015. 5197−5206
    [25] 安耀祖, 陆耀, 赵红. 一种自适应正则化的图像超分辨率算法. 自动化学报, 2012, 38(4): 601-608 doi: 10.3724/SP.J.1004.2012.00601

    An Yao-Zu, Lu Yao, Zhao Hong. An adaptive-regularized image super-resolution. Acta Automatica Sinica, 2012, 38(4): 601-608 doi: 10.3724/SP.J.1004.2012.00601
    [26] Tai Y, Yang J, Liu X, Xu C. Memnet: A persistent memory network for image restoration. In: Proceedings of the 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017. 4539−4547
    [27] Li Z, Yang J, Liu Z, Jeon G, Wu W. Feedback network for image super-resolution. In: Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019. 3867−3876
    [28] Qiu Y, Wang R, Tao D, Cheng J. Embedded block residual network: A recursive restoration model for single-image super-resolution. In: Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul, Korea: IEEE, 2019. 4180−4189
    [29] Chu X, Zhang B, Ma H, Xu R, Li Q. Fast, accurate and lightweight super-resolution with neural architecture search. In: Proceedings of the 25th International Conference on Pattern Recognition (ICPR). Milan, Italy: IEEE, 2021. 59−64
    [30] Chu X, Zhang B, Xu R. Multi-objective reinforced evolution in mobile neural architecture search. In: Proceedings of the 20th European Conference on Computer Vision. Glasgow, UK: Springer, 2020. 99−113
    [31] Luo X, Xie Y, Zhang Y, Qu Y, Li C, Fu Y. Latticenet: Towards lightweight image super-resolution with lattice block. In: Proceedings of the 20th European Conference on Computer Vision. Glasgow, UK: Springer, 2020. 23−28
    [32] Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City, USA: IEEE, 2018. 7132−7141
    [33] Wang X, Girshick R, Gupta A, He K. Non-local neural networks. In: Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City, USA: IEEE, 2018. 7794−7803
    [34] Liu D, Wen B, Fan Y, Loy C C, Huang T S. Non-local recurrent network for image restoration. Advances in Neural Information Processing Systems, 2018, 31
    [35] Mei Y, Fan Y, Zhou Y, Huang L, Huang T S, Shi, H. Image super-resolution with cross-scale non-local attention and exhaustive self-exemplars mining. In: Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE, 2020. 5690−5699
    [36] Niu B, Wen W, Ren W, Zhang X, Yang L, Wang S, et al. Single image super-resolution via a holistic attention network. In: Proceedings of the 20th European Conference on Computer Vision. Glasgow, UK: Springer, 2020. 191−207
    [37] Johnson J, Alahi A, Fei-Fei L. Perceptual losses for real-time style transfer and super-resolution. In: Proceedings of the 14th European Conference on Computer Vision. Amsterdam, Netherlands: Springer, 2016. 694−711
    [38] Ledig C, Theis L, Huszár F, Caballero J, Cunningham A, Acosta A, et al. Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017. 4681−4690
    [39] Yuan Y, Liu S, Zhang J, Zhang Y, Dong C, Lin L. Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks. In: Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City, USA: IEEE, 2018. 701−710
    [40] Yu J, Fan Y, Huang T. Wide activation for efficient image and video super-resolution. In: Proceedings of the 30th British Machine Vision Conference, BMVC 2019. Cardiff, UK: BMVA Press, 2020
    [41] Shi W, Caballero J, Huszár F, Totz J, Aitken A P, Bishop R, et al. 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. Las Vegas, USA: IEEE, 2016. 1874−1883
    [42] Howard A G, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications.[Online], available: https://arxiv.org/abs/1704.04861, April 17, 2017
    [43] Xie S, Girshick R, Dollár P, Tu Z, He K. Aggregated residual transformations for deep neural networks. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017. 1492−1500
    [44] Szegedy C, Ioffe S, Vanhoucke V, Alemi A A. Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the Thirty-first AAAI Conference on Artificial Intelligence. San Francisco, USA: AAAI Press, 2017
    [45] 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. Honolulu, USA: IEEE, 2017. 4700−4708
    [46] Zhang C, Benz P, Argaw D M, Lee S, Kim J, Rameau F, et al. Resnet or densenet? introducing dense shortcuts to resnet. In: Proceedings of the 2021 IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa, USA: IEEE, 2021. 550−3559
    [47] Zhao H, Shi J, Qi X, Wang X, Jia J. Pyramid scene parsing network. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017. 2881−2890
    [48] Timofte R, Agustsson E, Van Gool L, Yang M H, Zhang L. Ntire 2017 challenge on single image super-resolution: Methods and results. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu, USA: IEEE, 2017. 114−125
    [49] Bevilacqua M, Roumy A, Guillemot C, Alberi-Morel M L. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. The British Machine Vision Conference. 2012. 135−1
    [50] Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations. In: Proceedings of the International conference on curves and surfaces. Heidelberg, Berlin: Springer, 2010. 711−730
    [51] Arbelaez P, Maire M, Fowlkes C, Malik J. Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33(5): 898-916
    [52] Matsui Y, Ito K, Aramaki Y, Fujimoto A, Ogawa T, Yamasaki T, et al. Sketch-based manga retrieval using manga109 dataset. Multimedia Tools and Applications, 2017, 76(20): 21811-21838 doi: 10.1007/s11042-016-4020-z
    [53] Gao X, Lu W, Tao D, Li X. Image quality assessment based on multiscale geometric analysis. IEEE Transactions on Image Processing, 2009, 18(7): 1409-1423 doi: 10.1109/TIP.2009.2018014
    [54] Wang Z, 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 doi: 10.1109/TIP.2003.819861
    [55] Chollet F. Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017. 1251−1258
    [56] Lai W S, Huang J B, Ahuja N, Yang M H. Deep laplacian pyramid networks for fast and accurate super-resolution. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017. 624−632
    [57] Tai Y, Yang J, Liu X. Image super-resolution via deep recursive residual network. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017. 3147−3155
    [58] Zhang K, Zuo W, Zhang L. Learning a single convolutional super-resolution network for multiple degradations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. Salt Lake City, USA: IEEE, 2018. 3262−3271
    [59] Wang L, Dong X, Wang Y, Ying X, Lin Z, An W, et al. Exploring sparsity in image super-resolution for efficient inference. In: Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, USA: IEEE, 2021. 4917−4926
    [60] Luo X, Liang Q, Liu D, Qu Y. Boosting lightweight single image super-resolution via joint-distillation. In: Proceedings of the 29th ACM International Conference on Multimedia. Virtual Event: Association for Computing Machinery, 2021. 1535−1543
    [61] Zhao H, Kong X, He J, Qiao Y, Dong C. Efficient image super-resolution using pixel attention. In: Proceedings of the 2020 European Conference on Computer Vision. Cham, Netherlands: Springer, 2020. 56−72
    [62] Cai J, Zeng H, Yong H, Cao Z, Zhang L. Toward real-world single image super-resolution: A new benchmark and a new model. In: Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul, Korea: IEEE, 2019. 3086−3095
  • 加载中
计量
  • 文章访问数:  137
  • HTML全文浏览量:  95
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-11-17
  • 录用日期:  2022-06-17
  • 网络出版日期:  2022-07-30

目录

    /

    返回文章
    返回