电子学报 ›› 2022, Vol. 50 ›› Issue (10): 2336-2346.DOI: 10.12263/DZXB.20201089
周登文, 李文斌, 李金新, 黄志勇
收稿日期:
2020-09-30
修回日期:
2021-05-14
出版日期:
2022-10-25
作者简介:
ZHOU Deng-wen, LI Wen-bin, LI Jin-xin, HUANG Zhi-yong
Received:
2020-09-30
Revised:
2021-05-14
Online:
2022-10-25
Published:
2022-10-11
摘要:
近年来,基于深度卷积神经网络的图像超分辨率技术取得了突出进展,并主导了当前的超分辨率技术的研究.但是,性能的改进,往往以参数量的急剧增加为代价,这限制了超分辨率方法的实际应用.本文设计了一个轻量级单图像超分辨率深度卷积网络,主要贡献包括:提出了一个多尺度的特征融合模块,使用不同感受野的卷积核,提取多种尺度的特征;提出了一个通道搅乱注意力模块,促进特征通道之间的信息流动,并增强特征选择能力;提出了一个全局特征融合连接模块,提高浅层特征的利用率.实验证明,本文方法与当前代表性的方法MSRN(Multi-Scale Residual Network)相比,参数量减少了3/4,重建的高分辨率图像的主观和客观质量均显著更好.
中图分类号:
周登文, 李文斌, 李金新, 等. 一种轻量级的多尺度通道注意图像超分辨率重建网络[J]. 电子学报, 2022, 50(10): 2336-2346.
Deng-wen ZHOU, Wen-bin LI, Jin-xin LI, et al. Image Super-Resolution Reconstruction Based on Lightweight Multi-Scale Channel Attention Network[J]. Acta Electronica Sinica, 2022, 50(10): 2336-2346.
层名称 | 输入尺寸 | 输出尺寸 | 卷积核大小 |
---|---|---|---|
1×1卷积层 | H×W×64 | H×W×48 | 1×1 |
组卷积层 | H×W×48 | H×W×48 | 1×1 |
通道搅乱层 | H×W×48 | H×W×48 | — |
1×1卷积层 | H×W×48 | H×W×64 | 1×1 |
平均池化层 | 1×1×64 | 1×1×64 | — |
表1 通道搅乱注意力模块(CSAM)参数设置
层名称 | 输入尺寸 | 输出尺寸 | 卷积核大小 |
---|---|---|---|
1×1卷积层 | H×W×64 | H×W×48 | 1×1 |
组卷积层 | H×W×48 | H×W×48 | 1×1 |
通道搅乱层 | H×W×48 | H×W×48 | — |
1×1卷积层 | H×W×48 | H×W×64 | 1×1 |
平均池化层 | 1×1×64 | 1×1×64 | — |
层名称 | 输入尺寸 | 输出尺寸 | 卷积核大小 |
---|---|---|---|
3×3卷积层 | H×W×64 | H×W×64 | 3×3 |
Relu激活 | H×W×64 | H×W×64 | 5×5 |
5×5卷积层 | H×W×64 | H×W×64 | — |
Relu激活 | H×W×64 | H×W×64 | 1×1 |
合并(concat) | H×W×64 | H×W×128 | — |
1×1卷积层 | H×W×128 | H×W×64 | 1×1 |
表2 多尺度特征融合块(MSFFB) 参数设置
层名称 | 输入尺寸 | 输出尺寸 | 卷积核大小 |
---|---|---|---|
3×3卷积层 | H×W×64 | H×W×64 | 3×3 |
Relu激活 | H×W×64 | H×W×64 | 5×5 |
5×5卷积层 | H×W×64 | H×W×64 | — |
Relu激活 | H×W×64 | H×W×64 | 1×1 |
合并(concat) | H×W×64 | H×W×128 | — |
1×1卷积层 | H×W×128 | H×W×64 | 1×1 |
GFFC | × | √ | × | × | √ | √ | × | √ |
---|---|---|---|---|---|---|---|---|
CSAM | × | × | √ | × | √ | × | √ | √ |
MSFFB | × | × | × | √ | × | √ | √ | √ |
PSNR | 32.14 | 32.17 | 32.15 | 32.20 | 32.22 | 32.26 | 32.27 | 32.32 |
表3 多尺度特征融合块、通道搅乱注意力模块和全局特征融合连接在200个迭代周期、DIV2K验证集×4上的PSNR值
GFFC | × | √ | × | × | √ | √ | × | √ |
---|---|---|---|---|---|---|---|---|
CSAM | × | × | √ | × | √ | × | √ | √ |
MSFFB | × | × | × | √ | × | √ | √ | √ |
PSNR | 32.14 | 32.17 | 32.15 | 32.20 | 32.22 | 32.26 | 32.27 | 32.32 |
H和M数目 | PSNR/dB |
---|---|
1 | 32.14 |
2 | 32.25 |
3 | 32.32 |
表4 DIV2K验证集中递归块对网络性能影响
H和M数目 | PSNR/dB |
---|---|
1 | 32.14 |
2 | 32.25 |
3 | 32.32 |
放大 倍数 | 模型 | 参数量 | Set5 | Set14 | B100 | Urban100 | Manga109 |
---|---|---|---|---|---|---|---|
PSNR/SSIM | PSNR/SSIM | PSNR/SSIM | PSNR/SSIM | PSNR/SSIM | |||
×2 | SRCNN | 57K | 36.66/0.952 4 | 32.42/0.906 3 | 31.36/0.887 9 | 29.50/0.894 6 | 35.74/0.966 1 |
FSRCNN | 12K | 37.00/0.955 8 | 32.63/0.908 8 | 31.53/0.892 0 | 29.88/0.902 0 | 36.67/0.969 4 | |
VDSR | 665K | 37.53/0.958 7 | 33.03/0.912 4 | 31.90/0.896 0 | 30.76/0.914 0 | 37.22/0.972 9 | |
DRCN | 1774K | 37.63/0.958 8 | 33.04/0.911 8 | 31.85/0.894 2 | 30.75/0.913 3 | 37.63/0.972 3 | |
LapSRN | 813K | 37.52/0.959 0 | 33.08/0.913 0 | 31.80/0.895 0 | 30.41/0.910 0 | 37.27/0.974 0 | |
DRRN | 297K | 37.74/0.959 1 | 33.23/0.913 6 | 32.05/0.897 3 | 31.23/0.918 8 | 37.92/0.976 0 | |
MemNet | 677K | 37.78/0.959 7 | 33.28/0.914 2 | 32.08/0.897 8 | 31.31/0.919 5 | 37.72/0.974 0 | |
SRMDNF | 1513K | 37.79/0.960 0 | 33.32/0.915 0 | 32.05/0.898 0 | 31.33/0.920 0 | 38.07/0.976 1 | |
CARN | 1592K | 37.76/0.959 0 | 33.52/0.916 6 | 32.09/0.897 8 | 31.92/0.925 6 | 38.36/0.976 5 | |
CBPN | 1036K | 37.90/0.959 0 | 33.60/0.917 1 | 32.17/0.898 9 | 32.14/0.927 9 | — | |
IMDN | 694K | 38.00/0.960 5 | 33.63/0.917 7 | 32.19/0.899 6 | 32.17/0.928 3 | 38.88/0.977 4 | |
LFFN | 1522K | 37.95/0.959 7 | — | 32.20/0.899 4 | 32.39/0.929 9 | 38.73/0.976 5 | |
MSRN | 5930K | 38.08/0.960 7 | 33.70/0.918 6 | 32.29/0.930 3 | 38.69/0.977 2 | ||
MCSN | 1561K | 32.22/0.900 1 | |||||
MCSN+ | 1561K | 38.14/0.961 0 | 33.79/0.919 5 | 32.26/0.900 6 | 32.58/0.932 1 | 39.07/0.977 9 | |
×3 | SRCNN | 57K | 32.75/0.909 0 | 29.28/0.820 9 | 28.41/0.786 3 | 26.24/0.798 9 | 30.59/0.910 7 |
FSRCNN | 12K | 33.16/0.914 0 | 29.43/0.824 2 | 28.53/0.791 0 | 26.43/0.808 0 | 30.98/0.921 2 | |
VDSR | 665K | 33.66/0.921 3 | 29.77/0.831 4 | 28.82/0.797 6 | 27.14/0.827 9 | 32.01/0.931 0 | |
DRCN | 1774K | 33.82/0.922 6 | 29.76/0.831 1 | 28.80/0.796 3 | 27.15/0.827 6 | 32.31/0.932 8 | |
DRRN | 297K | 34.03/0.924 4 | 29.96/0.834 9 | 28.95/0.800 4 | 27.53/0.837 8 | 32.74/0.939 0 | |
MemNet | 677K | 34.09/0.924 8 | 30.00/0.835 0 | 28.96/0.800 1 | 27.56/0.837 6 | 32.51/0.936 9 | |
SRMDNF | 1530K | 34.12/0.925 0 | 30.04/0.837 0 | 28.97/0.803 0 | 27.57/0.840 0 | 33.00/0.940 3 | |
CARN | 1592K | 34.29/0.925 5 | 30.29/0.840 7 | 29.06/0.803 4 | 27.38/0.840 4 | 33.50/0.944 0 | |
IMDN | 703K | 34.36/0.927 0 | 30.32/0.841 7 | 29.09/0.804 6 | 28.17/0.851 9 | 33.61/0.944 5 | |
LFFN | 1534K | 34.43/0.926 6 | — | 29.13/0.805 9 | 28.34/0.855 8 | 33.65/0.944 5 | |
MSRN | 6114K | 34.46/0.927 8 | 30.41/0.843 7 | 28.33/0.856 1 | 33.67/0.945 6 | ||
MCSN | 1569K | 29.15/0.806 2 | 28.45/0.858 1 | 33.95/0.946 6 | |||
MCSN+ | 1569K | 34.59/0.928 7 | 30.49/0.844 8 | 29.20/0.807 2 | 28.61/0.860 4 | 34.18/0.947 8 | |
×4 | SRCNN | 57K | 30.48/0.862 8 | 27.49/0.750 3 | 26.90/0.710 1 | 24.52/0.722 1 | 27.66/0.850 5 |
FSRCNN | 12K | 30.71/0.865 7 | 27.59/0.753 5 | 26.98/0.715 0 | 24.62/0.728 0 | 27.90/0.851 7 | |
VDSR | 665K | 31.35/0.883 8 | 28.01/0.767 4 | 27.29/0.725 1 | 25.18/0.752 4 | 28.83/0.880 9 | |
DRCN | 1774K | 31.53/0.885 4 | 28.02/0.767 0 | 27.23/0.723 3 | 25.14/0.751 0 | 28.98/0.881 6 | |
LapSRN | 813K | 31.54/0.885 0 | 28.19/0.772 0 | 27.32/0.728 0 | 25.21/0.756 0 | 29.09/0.884 5 | |
DRRN | 297K | 31.68/0.888 8 | 28.21/0.772 0 | 27.38/0.728 4 | 25.44/0.763 8 | 29.46/0.896 0 | |
MemNet | 677K | 31.74/0.889 3 | 28.26/0.772 3 | 27.40/0.728 1 | 25.50/0.763 0 | 29.42/0.894 2 | |
SRMDNF | 1555K | 31.96/0.893 0 | 28.35/0.777 0 | 27.49/0.734 0 | 25.68/0.773 0 | 30.09/0.902 4 | |
CARN | 1592K | 32.13/0.893 7 | 28.60/0.780 6 | 27.58/0.734 9 | 26.07/0.783 7 | 30.47/0.908 4 | |
CBPN | 1197K | 32.21/0.894 4 | 28.63/0.781 3 | 27.58/0.735 6 | 26.14/0.786 9 | — | |
IMDN | 715K | 32.21/0.894 8 | 28.58/0.781 1 | 27.56/0.735 3 | 26.04/0.783 8 | 30.45/0.907 5 | |
LFFN | 1531K | 32.15/0.894 5 | — | 27.52/0.737 7 | 26.24/0.790 2 | 30.66/0.909 9 | |
MSRN | 6078K | 32.26/0.896 0 | 28.63/0.783 6 | 27.61/0.738 0 | 26.22/0.791 1 | 30.57/0.910 3 | |
MCSN | 1581K | ||||||
MCSN+ | 1581K | 32.50/0.898 3 | 28.81/0.786 1 | 27.70/0.739 8 | 26.50/0.796 7 | 31.06/0.914 8 | |
×8 | SRCNN | 57K | 25.34/0.647 1 | 23.86/0.544 3 | 24.14/0.504 3 | 21.29/0.513 3 | 22.46/0.660 6 |
FSRCNN | 12K | 25.42/0.644 0 | 23.94/0.548 2 | 24.21/0.511 2 | 21.32/0.509 0 | 22.39/0.635 7 | |
VDSR | 655K | 25.73/0.674 3 | 23.20/0.511 0 | 24.34/0.516 9 | 21.48/0.528 9 | 22.73/0.668 8 | |
DRCN | 1774K | 25.93/0.674 3 | 24.27/0.551 0 | 24.49/0.516 8 | 21.71/0.528 9 | 23.20/0.668 6 | |
LapSRN | 813K | 26.15/0.702 8 | 24.45/0.579 2 | 24.54/0.529 3 | 21.81/0.555 5 | 23.39/0.706 8 | |
MSRN | 6226K | 26.59/0.725 4 | 24.88/0.596 1 | 24.70/0.541 0 | 22.37/0.597 7 | 24.28/0.751 7 | |
MCSN | 1664K | ||||||
MCSN+ | 1664K | 27.12/0.778 6 | 25.05/0.643 2 | 24.84/0.598 2 | 22.55/0.620 2 | 24.68/0.782 3 |
表5 各种SISR方法的平均PSNR值与SSIM值
放大 倍数 | 模型 | 参数量 | Set5 | Set14 | B100 | Urban100 | Manga109 |
---|---|---|---|---|---|---|---|
PSNR/SSIM | PSNR/SSIM | PSNR/SSIM | PSNR/SSIM | PSNR/SSIM | |||
×2 | SRCNN | 57K | 36.66/0.952 4 | 32.42/0.906 3 | 31.36/0.887 9 | 29.50/0.894 6 | 35.74/0.966 1 |
FSRCNN | 12K | 37.00/0.955 8 | 32.63/0.908 8 | 31.53/0.892 0 | 29.88/0.902 0 | 36.67/0.969 4 | |
VDSR | 665K | 37.53/0.958 7 | 33.03/0.912 4 | 31.90/0.896 0 | 30.76/0.914 0 | 37.22/0.972 9 | |
DRCN | 1774K | 37.63/0.958 8 | 33.04/0.911 8 | 31.85/0.894 2 | 30.75/0.913 3 | 37.63/0.972 3 | |
LapSRN | 813K | 37.52/0.959 0 | 33.08/0.913 0 | 31.80/0.895 0 | 30.41/0.910 0 | 37.27/0.974 0 | |
DRRN | 297K | 37.74/0.959 1 | 33.23/0.913 6 | 32.05/0.897 3 | 31.23/0.918 8 | 37.92/0.976 0 | |
MemNet | 677K | 37.78/0.959 7 | 33.28/0.914 2 | 32.08/0.897 8 | 31.31/0.919 5 | 37.72/0.974 0 | |
SRMDNF | 1513K | 37.79/0.960 0 | 33.32/0.915 0 | 32.05/0.898 0 | 31.33/0.920 0 | 38.07/0.976 1 | |
CARN | 1592K | 37.76/0.959 0 | 33.52/0.916 6 | 32.09/0.897 8 | 31.92/0.925 6 | 38.36/0.976 5 | |
CBPN | 1036K | 37.90/0.959 0 | 33.60/0.917 1 | 32.17/0.898 9 | 32.14/0.927 9 | — | |
IMDN | 694K | 38.00/0.960 5 | 33.63/0.917 7 | 32.19/0.899 6 | 32.17/0.928 3 | 38.88/0.977 4 | |
LFFN | 1522K | 37.95/0.959 7 | — | 32.20/0.899 4 | 32.39/0.929 9 | 38.73/0.976 5 | |
MSRN | 5930K | 38.08/0.960 7 | 33.70/0.918 6 | 32.29/0.930 3 | 38.69/0.977 2 | ||
MCSN | 1561K | 32.22/0.900 1 | |||||
MCSN+ | 1561K | 38.14/0.961 0 | 33.79/0.919 5 | 32.26/0.900 6 | 32.58/0.932 1 | 39.07/0.977 9 | |
×3 | SRCNN | 57K | 32.75/0.909 0 | 29.28/0.820 9 | 28.41/0.786 3 | 26.24/0.798 9 | 30.59/0.910 7 |
FSRCNN | 12K | 33.16/0.914 0 | 29.43/0.824 2 | 28.53/0.791 0 | 26.43/0.808 0 | 30.98/0.921 2 | |
VDSR | 665K | 33.66/0.921 3 | 29.77/0.831 4 | 28.82/0.797 6 | 27.14/0.827 9 | 32.01/0.931 0 | |
DRCN | 1774K | 33.82/0.922 6 | 29.76/0.831 1 | 28.80/0.796 3 | 27.15/0.827 6 | 32.31/0.932 8 | |
DRRN | 297K | 34.03/0.924 4 | 29.96/0.834 9 | 28.95/0.800 4 | 27.53/0.837 8 | 32.74/0.939 0 | |
MemNet | 677K | 34.09/0.924 8 | 30.00/0.835 0 | 28.96/0.800 1 | 27.56/0.837 6 | 32.51/0.936 9 | |
SRMDNF | 1530K | 34.12/0.925 0 | 30.04/0.837 0 | 28.97/0.803 0 | 27.57/0.840 0 | 33.00/0.940 3 | |
CARN | 1592K | 34.29/0.925 5 | 30.29/0.840 7 | 29.06/0.803 4 | 27.38/0.840 4 | 33.50/0.944 0 | |
IMDN | 703K | 34.36/0.927 0 | 30.32/0.841 7 | 29.09/0.804 6 | 28.17/0.851 9 | 33.61/0.944 5 | |
LFFN | 1534K | 34.43/0.926 6 | — | 29.13/0.805 9 | 28.34/0.855 8 | 33.65/0.944 5 | |
MSRN | 6114K | 34.46/0.927 8 | 30.41/0.843 7 | 28.33/0.856 1 | 33.67/0.945 6 | ||
MCSN | 1569K | 29.15/0.806 2 | 28.45/0.858 1 | 33.95/0.946 6 | |||
MCSN+ | 1569K | 34.59/0.928 7 | 30.49/0.844 8 | 29.20/0.807 2 | 28.61/0.860 4 | 34.18/0.947 8 | |
×4 | SRCNN | 57K | 30.48/0.862 8 | 27.49/0.750 3 | 26.90/0.710 1 | 24.52/0.722 1 | 27.66/0.850 5 |
FSRCNN | 12K | 30.71/0.865 7 | 27.59/0.753 5 | 26.98/0.715 0 | 24.62/0.728 0 | 27.90/0.851 7 | |
VDSR | 665K | 31.35/0.883 8 | 28.01/0.767 4 | 27.29/0.725 1 | 25.18/0.752 4 | 28.83/0.880 9 | |
DRCN | 1774K | 31.53/0.885 4 | 28.02/0.767 0 | 27.23/0.723 3 | 25.14/0.751 0 | 28.98/0.881 6 | |
LapSRN | 813K | 31.54/0.885 0 | 28.19/0.772 0 | 27.32/0.728 0 | 25.21/0.756 0 | 29.09/0.884 5 | |
DRRN | 297K | 31.68/0.888 8 | 28.21/0.772 0 | 27.38/0.728 4 | 25.44/0.763 8 | 29.46/0.896 0 | |
MemNet | 677K | 31.74/0.889 3 | 28.26/0.772 3 | 27.40/0.728 1 | 25.50/0.763 0 | 29.42/0.894 2 | |
SRMDNF | 1555K | 31.96/0.893 0 | 28.35/0.777 0 | 27.49/0.734 0 | 25.68/0.773 0 | 30.09/0.902 4 | |
CARN | 1592K | 32.13/0.893 7 | 28.60/0.780 6 | 27.58/0.734 9 | 26.07/0.783 7 | 30.47/0.908 4 | |
CBPN | 1197K | 32.21/0.894 4 | 28.63/0.781 3 | 27.58/0.735 6 | 26.14/0.786 9 | — | |
IMDN | 715K | 32.21/0.894 8 | 28.58/0.781 1 | 27.56/0.735 3 | 26.04/0.783 8 | 30.45/0.907 5 | |
LFFN | 1531K | 32.15/0.894 5 | — | 27.52/0.737 7 | 26.24/0.790 2 | 30.66/0.909 9 | |
MSRN | 6078K | 32.26/0.896 0 | 28.63/0.783 6 | 27.61/0.738 0 | 26.22/0.791 1 | 30.57/0.910 3 | |
MCSN | 1581K | ||||||
MCSN+ | 1581K | 32.50/0.898 3 | 28.81/0.786 1 | 27.70/0.739 8 | 26.50/0.796 7 | 31.06/0.914 8 | |
×8 | SRCNN | 57K | 25.34/0.647 1 | 23.86/0.544 3 | 24.14/0.504 3 | 21.29/0.513 3 | 22.46/0.660 6 |
FSRCNN | 12K | 25.42/0.644 0 | 23.94/0.548 2 | 24.21/0.511 2 | 21.32/0.509 0 | 22.39/0.635 7 | |
VDSR | 655K | 25.73/0.674 3 | 23.20/0.511 0 | 24.34/0.516 9 | 21.48/0.528 9 | 22.73/0.668 8 | |
DRCN | 1774K | 25.93/0.674 3 | 24.27/0.551 0 | 24.49/0.516 8 | 21.71/0.528 9 | 23.20/0.668 6 | |
LapSRN | 813K | 26.15/0.702 8 | 24.45/0.579 2 | 24.54/0.529 3 | 21.81/0.555 5 | 23.39/0.706 8 | |
MSRN | 6226K | 26.59/0.725 4 | 24.88/0.596 1 | 24.70/0.541 0 | 22.37/0.597 7 | 24.28/0.751 7 | |
MCSN | 1664K | ||||||
MCSN+ | 1664K | 27.12/0.778 6 | 25.05/0.643 2 | 24.84/0.598 2 | 22.55/0.620 2 | 24.68/0.782 3 |
模型 | CARN | MSRN | IMDN | MCSN |
---|---|---|---|---|
时间/s | 0.040 | 0.045 | 0.046 | 0.067 |
PSNR/dB | 32.13 | 32.26 | 32.21 | 32.43 |
表6 Set5 ×4放大倍数下网络性能与运行时间对比
模型 | CARN | MSRN | IMDN | MCSN |
---|---|---|---|---|
时间/s | 0.040 | 0.045 | 0.046 | 0.067 |
PSNR/dB | 32.13 | 32.26 | 32.21 | 32.43 |
模型 | SAN | EBPN | ERN | MCSN |
---|---|---|---|---|
参数量(M) | 15.7 | 8.18 | 9.53 | 1.58 |
PSNR/dB | 32.64 | 32.79 | 32.39 | 32.43 |
表7 Set5 ×4放大倍数下最先进方法性能与参数量对比
模型 | SAN | EBPN | ERN | MCSN |
---|---|---|---|---|
参数量(M) | 15.7 | 8.18 | 9.53 | 1.58 |
PSNR/dB | 32.64 | 32.79 | 32.39 | 32.43 |
1 | THORNTON M W, ATKINSON P M, HOLLAND D A. Sub-pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super-resolution pixel-swapping[J]. International Journal of Remote Sensing, 2006, 27(3): 473-491. |
2 | ZOU W W W, YUEN P C. Very low resolution face recognition problem[J]. IEEE Transactions on Image Processing, 2012, 21(1): 327-340. |
3 | SHI W Z, CABALLERO J, LEDIG C, et al. Cardiac image super-resolution with global correspondence using multi-atlas patchmatch[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Heidelberg: Springer, 2013: 9-16. |
4 | LEDIG C, THEIS L, HUSZÁR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 105-114. |
5 | WANG F, JIANG M Q, QIAN C, et al. Residual attention network for image classification[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6450-6458. |
6 | LI Z, YANG J L, LIU Z, et al. Feedback network for image super-resolution[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Long Beach: IEEE, 2019: 3862-3871. |
7 | LIM B, SON S, KIM H, et al. Enhanced deep residual networks for single image super-resolution[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu: IEEE, 2017: 1132-1140. |
8 | ZHANG Y L, TIAN Y P, KONG Y, et al. Residual dense network for image super-resolution[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 2472-2481. |
9 | DONG C, LOY C C, HE K M, et al. Learning a Deep Convolutional Network for Image Super-Resolution[C]//European Conference on Computer Vision. Cham: Springer, 2014: 184-199. |
10 | KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 1646-1654. |
11 | HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778. |
12 | TAI Y, YANG J, LIU X M. Image super-resolution via deep recursive residual network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2790-2798. |
13 | TAI Y, YANG J, LIU X M, et al. MemNet: A persistent memory network for image restoration[C]//2017 IEEE International Conference on Computer Vision. Honolulu: IEEE, 2017: 4549-4557. |
14 | AHN N, KANG B, SOHN K A. Fast, accurate, and lightweight super-resolution with cascading residual network[C]//European Conference on Computer Vision. Cham: Springer International Publishing, 2018: 256-272. |
15 | ZHU F Y, ZHAO Q J. Efficient single image super-resolution via hybrid residual feature learning with compact back-projection network[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop. Seoul: IEEE, 2019: 2453-2460. |
16 | HUI Z, GAO X B, YANG Y C, et al. Lightweight image super-resolution with information multi-distillation network[C]//MM'19: Proceedings of the 27th ACM International Conference on Multimedia. New York: ACM, 2019: 2024-2032. |
17 | LI J C, FANG F M, MEI K F, et al. Multi-scale residual network for image super-resolution[C]//European Conference on Computer Vision. Cham: Springer International Publishing, 2018: 527-542. |
18 | ITTI L, KOCH C, NIEBUR E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259. |
19 | HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141. |
20 | ZHANG Y L, LI K P, LI K, et al. Image super-resolution using very deep residual channel attention networks[C]//European Conference on Computer Vision. Cham: Springer, 2018: 294-310. |
21 | KIM J, LEE J K, LEE K M. Deeply-recursive convolutional network for image super-resolution[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 1637-1645. |
22 | SHI W Z, CABALLERO J, HUSZÁR F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 1874-1883. |
23 | ZHANG Y L, LI K P, LI K, et al. Image super-resolution using very deep residual channel attention networks[C]//European Conference on Computer Vision. Cham: Springer, 2018: 294-310. |
24 | ZHANG X Y, ZHOU X Y, LIN M X, et al. ShuffleNet: An extremely efficient convolutional neural network for mobile devices[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 6848-6856. |
25 | AGUSTSSON E, TIMOFTE R. NTIRE 2017 challenge on single image super-resolution: Dataset and study[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Honolulu: IEEE, 2017: 1122-1131. |
26 | BEVILACQUA M, ROUMY A, GUILLEMOT C, et al. Low-complexity single-image super-resolution based on nonnegative neighbor embedding[C]//Proceedings British Machine Vision Conference. Surrey: BMVA Press, 2012: 135.1-135.10. |
27 | ZEYDE R, ELAD M, PROTTER M. On Single Image Scale-up Using Sparse-Representations[M]//Curves and Surfaces. Berlin, Heidelberg: Springer, 2012: 711-730. |
28 | 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 Eighth IEEE International Conference on Computer Vision. Vancouver: IEEE, 2001: 416-423. |
29 | HUANG J B, SINGH A, AHUJA N. Single image super-resolution from transformed self-exemplars[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 5197-5206. |
30 | MATSUI Y, ITO K, ARAMAKI Y, et al. Sketch-based manga retrieval using manga109 dataset[J]. Multimedia Tools and Applications, 2017, 76(20): 21811-21838. |
31 | WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: From error visibility to structural similarity[J]. IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society, 2004, 13(4): 600-612. |
32 | KINGMA D P, BA J. Adam: A method for stochastic optimization[EB/OL]. (2014)[2020]. . |
33 | PASZKE A, GROSS S, CHINTALA S, et al. Automatic differentiation in pytorch[OL]. (2017)[2020]. . |
34 | ZHANG K, ZUO W M, ZHANG L. Learning a single convolutional super-resolution network for multiple degradations[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 3262-3271. |
35 | DONG C, LOY C C, TANG X O. Accelerating the super-resolution convolutional neural network[C]//European Conference on Computer Vision. Cham: Springer, 2016: 391-407. |
36 | LAI W S, HUANG J B, AHUJA N, et al. Deep Laplacian pyramid networks for fast and accurate super-resolution[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 5835-5843. |
37 | YANG W M, WANG W, ZHANG X C, et al. Lightweight feature fusion network for single image super-resolution[J]. IEEE Signal Processing Letters, 2019, 26(4): 538-542. |
38 | DAI T, CAI J R, ZHANG Y B, et al. Second-order attention network for single image super-resolution[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 11057-11066. |
39 | QIU Y J, WANG R X, TAO D P, et al. Embedded block residual network: A recursive restoration model for single-image super-resolution[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 4179-4188. |
40 | HE X Y, MO Z T, WANG P S, et al. ODE-inspired network design for single image super-resolution[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Long Beach: IEEE, 2019: 1732-1741. |
41 | LAN R S, SUN L, LIU Z B, et al. Cascading and enhanced residual networks for accurate single-image super-resolution[J]. IEEE Transactions on Cybernetics, 2020, 51(1): 115-125. |
42 | TIMOFTE R, ROTHE R, VAN GOOL L. Seven ways to improve example-based single image super resolution[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 1865-1873. |
[1] | 李钦, 刘伟, 牛朝阳, 宝音图, 惠周勃. 低信噪比下基于分裂EfficientNet网络的雷达信号调制方式识别[J]. 电子学报, 2023, 51(3): 675-686. |
[2] | 隗昊, 唐焕玲, 周爱, 张益嘉, 陈飞, 鲁明羽. 基于双路分段注意力神经张量网络的临床文本关系抽取[J]. 电子学报, 2023, 51(3): 658-665. |
[3] | 黄赟, 张帆, 郭威, 陈立, 羊光. 一种基于数据标准差的卷积神经网络量化方法[J]. 电子学报, 2023, 51(3): 639-647. |
[4] | 范兵兵, 何庭建, 张聪炫, 陈震, 黎明. 联合遮挡约束与残差补偿的特征金字塔光流计算方法[J]. 电子学报, 2023, 51(3): 648-657. |
[5] | 吕杭, 蒋明峰, 李杨, 张鞠成, 王志康. 基于混合时频域特征的卷积神经网络心律失常分类方法的研究[J]. 电子学报, 2023, 51(3): 701-711. |
[6] | 张聿远, 闫文君, 张立民. 基于多模态特征融合网络的空时分组码识别算法[J]. 电子学报, 2023, 51(2): 489-498. |
[7] | 许新征, 李杉. 基于特征膨胀卷积模块的轻量化技术研究[J]. 电子学报, 2023, 51(2): 355-364. |
[8] | 丁琪, 田萱, 孙国栋. 基于注意力增强的热点感知新闻推荐模型[J]. 电子学报, 2023, 51(1): 93-104. |
[9] | 李滔, 董秀成, 林宏伟. 基于深监督跨尺度注意力网络的深度图像超分辨率重建[J]. 电子学报, 2023, 51(1): 128-138. |
[10] | 郭晓轩, 冯其波, 冀振燕, 郑发家, 杨燕燕. 多线激光光条图像缺陷分割模型研究[J]. 电子学报, 2023, 51(1): 172-179. |
[11] | 贾童瑶, 卓力, 李嘉锋, 张菁. 基于深度学习的单幅图像去雾研究进展[J]. 电子学报, 2023, 51(1): 231-245. |
[12] | 何滢婕, 刘月峰, 边浩东, 郭威, 张小燕. 基于Informer的电池荷电状态估算及其稀疏优化方法[J]. 电子学报, 2023, 51(1): 50-56. |
[13] | 王硕, 王坚, 王亚男, 宋亚飞. 一种基于特征融合的恶意代码快速检测方法[J]. 电子学报, 2023, 51(1): 57-66. |
[14] | 张永梅, 孙捷. 基于动静态特征双输入神经网络的咳嗽声诊断COVID-19算法[J]. 电子学报, 2023, 51(1): 202-212. |
[15] | 袁海英, 成君鹏, 曾智勇, 武延瑞. Mobile_BLNet:基于Big-Little Net的轻量级卷积神经网络优化设计[J]. 电子学报, 2023, 51(1): 180-191. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||