《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (5): 1579-1587.DOI: 10.11772/j.issn.1001-9081.2023050689
所属专题: 多媒体计算与计算机仿真
郭琳1,2,3, 刘坤虎1(), 马晨阳1, 来佑雪1, 徐映芬1
收稿日期:
2023-06-01
修回日期:
2023-09-01
接受日期:
2023-09-12
发布日期:
2023-09-14
出版日期:
2024-05-10
通讯作者:
刘坤虎
作者简介:
郭琳(1978—),女,湖北随州人,副教授,博士,主要研究方向:信号处理、机器视觉、深度学习基金资助:
Lin GUO1,2,3, Kunhu LIU1(), Chenyang MA1, Youxue LAI1, Yingfen XU1
Received:
2023-06-01
Revised:
2023-09-01
Accepted:
2023-09-12
Online:
2023-09-14
Published:
2024-05-10
Contact:
Kunhu LIU
About author:
GUO Lin, born in 1978, Ph. D., associate professor. Her research interests include signal processing, machine vision, deep learning.Supported by:
摘要:
针对现有残差网络存在残差特征利用不充分、细节丢失的问题,提出一种结合两层残差聚合结构和感受野扩展双注意力机制的深度神经网络模型,用于单幅图像超分辨率(SISR)重建。该模型通过跳跃连接形成两层嵌套的残差聚合网络结构,对网络各层提取的大量残差信息进行分层聚集和融合,能减少包含图像细节的残差信息的丢失。同时,设计一种多尺度感受野扩展模块,能捕获更大范围、不同尺度的上下文相关信息,促进深层残差特征的有效提取;并引入空间-通道双注意力机制,增强残差网络的判别性学习能力,提高重建图像质量。在数据集Set5、Set14、BSD100和Urban100上进行重建实验,并从客观指标和主观视觉效果上将所提模型与主流模型进行比较。客观评价结果表明,所提模型在全部4个测试数据集上均优于对比模型,其中,相较于经典的超分辨率卷积神经网络(SRCNN)模型和性能次优的对比模型ISRN(Iterative Super-Resolution Network),在放大2倍、3倍、4倍时的平均峰值信噪比(PSNR)分别提升1.91、1.71、1.61 dB和0.06、0.04、0.04 dB;视觉效果对比显示,所提模型恢复的图像细节纹理更清晰。
中图分类号:
郭琳, 刘坤虎, 马晨阳, 来佑雪, 徐映芬. 基于感受野扩展残差注意力网络的图像超分辨率重建[J]. 计算机应用, 2024, 44(5): 1579-1587.
Lin GUO, Kunhu LIU, Chenyang MA, Youxue LAI, Yingfen XU. Image super-resolution reconstruction based on residual attention network with receptive field expansion[J]. Journal of Computer Applications, 2024, 44(5): 1579-1587.
Input | RDAN1 | RDAN2 | RDAN3 | RDAN4 | Concat | Conv |
---|---|---|---|---|---|---|
64 | 64 | 64 | 64 | 64 | 256 | 64 |
表1 RF模块中各层的通道数
Tab. 1 Number of channels in each layer of RF model
Input | RDAN1 | RDAN2 | RDAN3 | RDAN4 | Concat | Conv |
---|---|---|---|---|---|---|
64 | 64 | 64 | 64 | 64 | 256 | 64 |
SA | CA | Concatenate | Conv | ||||
---|---|---|---|---|---|---|---|
输入 | GN | Conv | 输入 | GAP | Conv1d | ||
32 | 32 | 32 | 32 | 32 | 32 | 64 | 64 |
表2 SCA模块中各层的通道数
Tab. 2 Number of channels in each layer of SCA model
SA | CA | Concatenate | Conv | ||||
---|---|---|---|---|---|---|---|
输入 | GN | Conv | 输入 | GAP | Conv1d | ||
32 | 32 | 32 | 32 | 32 | 32 | 64 | 64 |
尺度 | 模型 | Set5 | Set14 | BSD100 | Urban100 | ||||
---|---|---|---|---|---|---|---|---|---|
PSNR/dB | SSIM | PSNR/dB | SSIM | PSNR/dB | SSIM | PSNR/dB | SSIM | ||
×2 | Bicubic | 33.66 | 0.929 9 | 30.24 | 0.868 8 | 29.56 | 0.843 1 | 26.88 | 0.840 3 |
SRCNN[ | 36.66 | 0.954 2 | 32.45 | 0.906 7 | 31.36 | 0.887 9 | 29.50 | 0.894 6 | |
DRCN[ | 37.63 | 0.958 8 | 33.04 | 0.911 8 | 31.85 | 0.894 2 | 30.75 | 0.913 3 | |
SRFBN-S[ | 37.78 | 0.955 7 | 33.35 | 0.915 6 | 32.00 | 0.897 0 | 31.41 | 0.920 7 | |
CARN[ | 37.76 | 0.959 0 | 33.52 | 0.916 6 | 32.09 | 0.897 8 | 31.92 | 0.925 6 | |
RFDN[ | 38.05 | 0.960 6 | 33.68 | 0.918 4 | 32.16 | 0.899 4 | 32.12 | 0.927 8 | |
SwinIR[ | 38.14 | 0.961 1 | 33.86 | 0.920 6 | 32.31 | 0.901 2 | 32.76 | 0.934 0 | |
EDSR[ | 38.11 | 0.960 2 | 33.92 | 0.919 5 | 32.32 | 0.901 3 | 32.93 | 0.935 1 | |
RDN[ | 38.24 | 0.921 2 | 32.34 | 0.901 7 | 32.89 | 0.935 3 | |||
MHFN[ | — | — | 33.79 | 0.919 6 | 32.20 | 0.899 8 | 32.40 | 0.930 1 | |
ISRN[ | 0.961 3 | 33.84 | |||||||
本文RFE-RAN | 38.19 | 0.961 7 | 34.05 | 0.921 3 | 32.38 | 0.902 8 | 32.97 | 0.936 5 | |
×3 | Bicubic | 30.39 | 0.868 2 | 27.55 | 0.774 2 | 27.21 | 0.738 5 | 24.46 | 0.734 9 |
SRCNN[ | 32.75 | 0.909 0 | 29.30 | 0.821 5 | 28.41 | 0.786 3 | 26.24 | 0.798 9 | |
DRCN[ | 33.82 | 0.922 6 | 29.76 | 0.831 1 | 28.80 | 0.796 3 | 27.15 | 0.827 6 | |
SRFBN-S[ | 34.20 | 0.925 5 | 30.10 | 0.837 2 | 28.96 | 0.801 0 | 27.66 | 0.841 5 | |
CARN[ | 34.29 | 0.925 5 | 30.29 | 0.840 7 | 29.06 | 0.803 4 | 27.38 | 0.840 4 | |
RFDN[ | 34.41 | 0.927 3 | 30.34 | 0.842 0 | 29.09 | 0.805 0 | 28.21 | 0.852 5 | |
SwinIR[ | 34.62 | 0.928 9 | 30.54 | 0.846 3 | 29.20 | 0.808 2 | 28.66 | 0.862 4 | |
EDSR[ | 34.65 | 0.928 0 | 30.52 | 0.846 2 | 29.25 | 0.809 3 | 28.80 | 0.865 3 | |
RDN[ | 34.71 | 30.57 | 0.846 8 | 0.809 3 | 28.80 | 0.865 3 | |||
MHFN[ | — | — | 30.40 | 0.842 8 | 29.13 | 0.805 6 | 28.35 | 0.855 7 | |
ISRN[ | 0.929 4 | 29.25 | |||||||
本文RFE-RAN | 34.71 | 0.929 9 | 30.62 | 0.847 9 | 29.29 | 0.811 4 | 28.89 | 0.867 3 | |
×4 | Bicubic | 28.42 | 0.810 4 | 26.00 | 0.702 7 | 25.96 | 0.667 5 | 23.14 | 0.657 7 |
SRCNN[ | 30.48 | 0.862 8 | 27.50 | 0.751 3 | 26.90 | 0.710 1 | 24.52 | 0.722 1 | |
DRCN[ | 31.53 | 0.885 4 | 28.02 | 0.767 0 | 27.23 | 0.723 3 | 25.14 | 0.751 0 | |
SRFBN-S[ | 31.98 | 0.892 3 | 28.45 | 0.777 9 | 27.44 | 0.731 3 | 25.71 | 0.771 9 | |
CARN[ | 32.13 | 0.893 7 | 28.60 | 0.780 6 | 27.58 | 0.734 9 | 26.07 | 0.783 7 | |
RFDN[ | 32.24 | 0.895 2 | 28.61 | 0.781 9 | 27.57 | 0.736 0 | 26.11 | 0.785 8 | |
SwinIR[ | 32.44 | 0.897 6 | 28.77 | 0.785 8 | 27.69 | 0.740 6 | 26.47 | 0.798 0 | |
EDSR[ | 32.46 | 0.896 8 | 28.80 | 0.787 6 | 27.71 | 0.742 0 | |||
RDN[ | 32.47 | 0.899 0 | 0.787 1 | 27.72 | 0.741 9 | 26.61 | 0.802 8 | ||
MHFN[ | — | — | 28.66 | 0.783 0 | 27.61 | 0.737 1 | 26.27 | 0.790 9 | |
ISRN[ | 32.55 | 28.79 | |||||||
本文RFE-RAN | 0.899 7 | 28.82 | 0.787 6 | 27.75 | 0.743 9 | 26.71 | 0.805 2 |
表3 各对比模型在4个实验数据集上的平均PSNR和SSIM值对比
Tab. 3 Comparison of average PSNR and SSIM values for comparison models on four experimental datasets
尺度 | 模型 | Set5 | Set14 | BSD100 | Urban100 | ||||
---|---|---|---|---|---|---|---|---|---|
PSNR/dB | SSIM | PSNR/dB | SSIM | PSNR/dB | SSIM | PSNR/dB | SSIM | ||
×2 | Bicubic | 33.66 | 0.929 9 | 30.24 | 0.868 8 | 29.56 | 0.843 1 | 26.88 | 0.840 3 |
SRCNN[ | 36.66 | 0.954 2 | 32.45 | 0.906 7 | 31.36 | 0.887 9 | 29.50 | 0.894 6 | |
DRCN[ | 37.63 | 0.958 8 | 33.04 | 0.911 8 | 31.85 | 0.894 2 | 30.75 | 0.913 3 | |
SRFBN-S[ | 37.78 | 0.955 7 | 33.35 | 0.915 6 | 32.00 | 0.897 0 | 31.41 | 0.920 7 | |
CARN[ | 37.76 | 0.959 0 | 33.52 | 0.916 6 | 32.09 | 0.897 8 | 31.92 | 0.925 6 | |
RFDN[ | 38.05 | 0.960 6 | 33.68 | 0.918 4 | 32.16 | 0.899 4 | 32.12 | 0.927 8 | |
SwinIR[ | 38.14 | 0.961 1 | 33.86 | 0.920 6 | 32.31 | 0.901 2 | 32.76 | 0.934 0 | |
EDSR[ | 38.11 | 0.960 2 | 33.92 | 0.919 5 | 32.32 | 0.901 3 | 32.93 | 0.935 1 | |
RDN[ | 38.24 | 0.921 2 | 32.34 | 0.901 7 | 32.89 | 0.935 3 | |||
MHFN[ | — | — | 33.79 | 0.919 6 | 32.20 | 0.899 8 | 32.40 | 0.930 1 | |
ISRN[ | 0.961 3 | 33.84 | |||||||
本文RFE-RAN | 38.19 | 0.961 7 | 34.05 | 0.921 3 | 32.38 | 0.902 8 | 32.97 | 0.936 5 | |
×3 | Bicubic | 30.39 | 0.868 2 | 27.55 | 0.774 2 | 27.21 | 0.738 5 | 24.46 | 0.734 9 |
SRCNN[ | 32.75 | 0.909 0 | 29.30 | 0.821 5 | 28.41 | 0.786 3 | 26.24 | 0.798 9 | |
DRCN[ | 33.82 | 0.922 6 | 29.76 | 0.831 1 | 28.80 | 0.796 3 | 27.15 | 0.827 6 | |
SRFBN-S[ | 34.20 | 0.925 5 | 30.10 | 0.837 2 | 28.96 | 0.801 0 | 27.66 | 0.841 5 | |
CARN[ | 34.29 | 0.925 5 | 30.29 | 0.840 7 | 29.06 | 0.803 4 | 27.38 | 0.840 4 | |
RFDN[ | 34.41 | 0.927 3 | 30.34 | 0.842 0 | 29.09 | 0.805 0 | 28.21 | 0.852 5 | |
SwinIR[ | 34.62 | 0.928 9 | 30.54 | 0.846 3 | 29.20 | 0.808 2 | 28.66 | 0.862 4 | |
EDSR[ | 34.65 | 0.928 0 | 30.52 | 0.846 2 | 29.25 | 0.809 3 | 28.80 | 0.865 3 | |
RDN[ | 34.71 | 30.57 | 0.846 8 | 0.809 3 | 28.80 | 0.865 3 | |||
MHFN[ | — | — | 30.40 | 0.842 8 | 29.13 | 0.805 6 | 28.35 | 0.855 7 | |
ISRN[ | 0.929 4 | 29.25 | |||||||
本文RFE-RAN | 34.71 | 0.929 9 | 30.62 | 0.847 9 | 29.29 | 0.811 4 | 28.89 | 0.867 3 | |
×4 | Bicubic | 28.42 | 0.810 4 | 26.00 | 0.702 7 | 25.96 | 0.667 5 | 23.14 | 0.657 7 |
SRCNN[ | 30.48 | 0.862 8 | 27.50 | 0.751 3 | 26.90 | 0.710 1 | 24.52 | 0.722 1 | |
DRCN[ | 31.53 | 0.885 4 | 28.02 | 0.767 0 | 27.23 | 0.723 3 | 25.14 | 0.751 0 | |
SRFBN-S[ | 31.98 | 0.892 3 | 28.45 | 0.777 9 | 27.44 | 0.731 3 | 25.71 | 0.771 9 | |
CARN[ | 32.13 | 0.893 7 | 28.60 | 0.780 6 | 27.58 | 0.734 9 | 26.07 | 0.783 7 | |
RFDN[ | 32.24 | 0.895 2 | 28.61 | 0.781 9 | 27.57 | 0.736 0 | 26.11 | 0.785 8 | |
SwinIR[ | 32.44 | 0.897 6 | 28.77 | 0.785 8 | 27.69 | 0.740 6 | 26.47 | 0.798 0 | |
EDSR[ | 32.46 | 0.896 8 | 28.80 | 0.787 6 | 27.71 | 0.742 0 | |||
RDN[ | 32.47 | 0.899 0 | 0.787 1 | 27.72 | 0.741 9 | 26.61 | 0.802 8 | ||
MHFN[ | — | — | 28.66 | 0.783 0 | 27.61 | 0.737 1 | 26.27 | 0.790 9 | |
ISRN[ | 32.55 | 28.79 | |||||||
本文RFE-RAN | 0.899 7 | 28.82 | 0.787 6 | 27.75 | 0.743 9 | 26.71 | 0.805 2 |
模型 | 参数量/MB | PSNR/dB | 模型 | 参数量/MB | PSNR/dB |
---|---|---|---|---|---|
EDSR | 43.08 | 32.32 | MHFN | 1.43 | 32.20 |
RDN | 22.30 | 32.34 | RFE-RAN | 15.63 | 32.38 |
ISRN | 3.50 | 32.35 |
表4 各模型的参数量及PSNR
Tab. 4 Number of parameters and PSNR of each model
模型 | 参数量/MB | PSNR/dB | 模型 | 参数量/MB | PSNR/dB |
---|---|---|---|---|---|
EDSR | 43.08 | 32.32 | MHFN | 1.43 | 32.20 |
RDN | 22.30 | 32.34 | RFE-RAN | 15.63 | 32.38 |
ISRN | 3.50 | 32.35 |
模型编号 | 模块数 | 参数量/MB | PSNR/dB | ||
---|---|---|---|---|---|
MM | RF | Set14 | Urban100 | ||
1 | 4 | 8 | 6.08 | 33.77 | 32.68 |
2 | 8 | 8 | 12.24 | 33.82 | 32.76 |
3 | 4 | 16 | 13.10 | 33.83 | 32.79 |
4 | 16 | 4 | 12.41 | 33.92 | 32.92 |
5 | 20 | 4 | 15.63 | 33.93 | 32.94 |
表5 不同模块数下模型的参数量和PSNR
Tab. 5 Number of parameters and PSNR of model with different blocks
模型编号 | 模块数 | 参数量/MB | PSNR/dB | ||
---|---|---|---|---|---|
MM | RF | Set14 | Urban100 | ||
1 | 4 | 8 | 6.08 | 33.77 | 32.68 |
2 | 8 | 8 | 12.24 | 33.82 | 32.76 |
3 | 4 | 16 | 13.10 | 33.83 | 32.79 |
4 | 16 | 4 | 12.41 | 33.92 | 32.92 |
5 | 20 | 4 | 15.63 | 33.93 | 32.94 |
模型编号 | CA | SA | RFE | PSNR/dB |
---|---|---|---|---|
1 | × | × | × | 30.21 |
2 | √ | × | × | 30.16 |
3 | × | √ | × | 30.28 |
4 | √ | √ | × | 30.37 |
表6 消融实验结果
Tab. 6 Ablation experiment results
模型编号 | CA | SA | RFE | PSNR/dB |
---|---|---|---|---|
1 | × | × | × | 30.21 |
2 | √ | × | × | 30.16 |
3 | × | √ | × | 30.28 |
4 | √ | √ | × | 30.37 |
数据集 | 尺度 | RAN | RFE-RAN | ||
---|---|---|---|---|---|
PSNR/dB | SSIM | PSNR/dB | SSIM | ||
Set5 | ×2 | 38.15 | 0.961 6 | 38.19 | 0.961 7 |
×3 | 34.68 | 0.929 7 | 34.71 | 0.929 9 | |
×4 | 32.53 | 0.899 9 | 32.54 | 0.899 7 | |
Set14 | ×2 | 33.93 | 0.921 2 | 34.05 | 0.921 3 |
×3 | 30.55 | 0.846 6 | 30.62 | 0.847 9 | |
×4 | 28.81 | 0.787 4 | 28.82 | 0.787 6 | |
BSD100 | ×2 | 32.29 | 0.901 7 | 32.38 | 0.902 8 |
×3 | 29.26 | 0.810 5 | 29.29 | 0.811 4 | |
×4 | 27.72 | 0.742 6 | 27.75 | 0.743 9 | |
Urban100 | ×2 | 32.73 | 0.933 7 | 32.97 | 0.936 5 |
×3 | 28.77 | 0.864 1 | 28.89 | 0.867 3 | |
×4 | 26.60 | 0.801 2 | 26.70 | 0.805 2 |
表7 RFE模块对本文模型在不同数据集上性能的影响
Tab. 7 Influence of RFE module to proposed model on different datasets
数据集 | 尺度 | RAN | RFE-RAN | ||
---|---|---|---|---|---|
PSNR/dB | SSIM | PSNR/dB | SSIM | ||
Set5 | ×2 | 38.15 | 0.961 6 | 38.19 | 0.961 7 |
×3 | 34.68 | 0.929 7 | 34.71 | 0.929 9 | |
×4 | 32.53 | 0.899 9 | 32.54 | 0.899 7 | |
Set14 | ×2 | 33.93 | 0.921 2 | 34.05 | 0.921 3 |
×3 | 30.55 | 0.846 6 | 30.62 | 0.847 9 | |
×4 | 28.81 | 0.787 4 | 28.82 | 0.787 6 | |
BSD100 | ×2 | 32.29 | 0.901 7 | 32.38 | 0.902 8 |
×3 | 29.26 | 0.810 5 | 29.29 | 0.811 4 | |
×4 | 27.72 | 0.742 6 | 27.75 | 0.743 9 | |
Urban100 | ×2 | 32.73 | 0.933 7 | 32.97 | 0.936 5 |
×3 | 28.77 | 0.864 1 | 28.89 | 0.867 3 | |
×4 | 26.60 | 0.801 2 | 26.70 | 0.805 2 |
1 | YANG J, WRIGHT J, HUANG T S, et al. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2861-2873. 10.1109/tip.2010.2050625 |
2 | TIMOFTE R, DE SMET V, VAN GOOL L. A+: adjusted anchored neighborhood regression for fast super-resolution[C]// Proceedings of 12th Asian Conference on Computer Vision. Cham: Springer, 2014: 111-126. 10.1007/978-3-319-16817-3_8 |
3 | DONG C, LOY C C, HE K, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307. 10.1109/tpami.2015.2439281 |
4 | 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. Piscataway: IEEE, 2016: 1646-1654. 10.1109/cvpr.2016.182 |
5 | KIM J, LEE J K, LEE K M. Deeply-recursive convolutional network for image super-resolution[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 1637-1645. 10.1109/cvpr.2016.181 |
6 | QU Y, LIN L, SHEN F, et al. Joint hierarchical category structure learning and large-scale image classification[J]. IEEE Transactions on Image Processing, 2017, 26(9): 4331-4346. 10.1109/tip.2016.2615423 |
7 | HE K, ZHANG X, REN S, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification [C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 1026-1034. 10.1109/iccv.2015.123 |
8 | LAI W-S, HUANG J-B, NARENDRA A, et al. Deep Laplacian pyramid networks for fast and accurate super-resolution[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 5835-5843. 10.1109/cvpr.2017.618 |
9 | LIM B, SON S, KIM H, et al. Enhanced deep residual networks for single image super-resolution[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2017: 1132-1140. 10.1109/cvprw.2017.151 |
10 | AHN N, KANG B, K-A SOHN. Fast, accurate, and lightweight super-resolution with cascading residual network[C]// Proceedings of the 15th European Conference on Computer Vision. Berlin: Springer, 2018: 256-272. 10.1007/978-3-030-01249-6_16 |
11 | ZHANG Y, LI K, LI K, et al. Image super-resolution using very deep residual channel attention networks[C]// Proceedings of the 15th European Conference on Computer Vision. Berlin: Springer, 2018: 286-301. 10.1007/978-3-030-01234-2_18 |
12 | ZHANG Y L, TIAN Y, KONG Y, et al. Residual dense network for image super-resolution[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 2472-2481. 10.1109/cvpr.2018.00262 |
13 | 王汇丰, 徐岩, 魏一铭, 等. 基于并联卷积与残差网络的图像超分辨率重建[J]. 计算机应用, 2022, 42(5): 1570-1576. 10.11772/j.issn.1001-9081.2021050742 |
WANG H F, XU Y, WEI Y M, et al. Image super-resolution reconstruction based on parallel convolution and residual network[J]. Journal of Computer Applications, 2022, 42(5): 1570-1576. 10.11772/j.issn.1001-9081.2021050742 | |
14 | 申利华, 李波. 基于特征金字塔网络和密集网络的肺部CT图像超分辨率重建[J]. 计算机应用, 2023, 43(5):1612-1619. 10.11772/j.issn.1001-9081.2022040620 |
SHEN L H, LI B. Super-resolution reconstruction of lung CT images based on feature pyramid network and dense network[J]. Journal of Computer Applications, 2023, 43(5):1612-1619. 10.11772/j.issn.1001-9081.2022040620 | |
15 | LI Z, YANG J, LIU Z, et al. Feedback network for image super-resolution[C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 3862-3871. 10.1109/cvpr.2019.00399 |
16 | 李金新,黄志勇,李文斌,等. 基于多层次特征融合的图像超分辨率重建[J]. 自动化学报,2023,49(1): 161-171. |
LI J X, HUANG Z Y, LI W B, et al. Image super-resolution based on multi-level feature fusion [J]. Acta Automatica Sinica, 2023,49(1): 161-171. | |
17 | LIU Y, WANG S, ZHANG J, et al. Iterative network for image super-resolution [J]. IEEE Transaction on Multimedia, 2022, 24: 2259-2272. 10.1109/tmm.2021.3078615 |
18 | SHI W, CABALLERO J, HUSZÁR F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 1874-1883. 10.1109/cvpr.2016.207 |
19 | HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141. 10.1109/cvpr.2018.00745 |
20 | LIU J, TANG J, WU G. Residual feature distillation network for lightweight image super-resolution[C]// Proceedings of the 16th European Conference on Computer Vision. Berlin: Springer, 2020: 41- 55. 10.1007/978-3-030-67070-2_2 |
21 | LIANG J, CAO J, SUN G, et al. SwinIR: image restoration using Swin Transformer[C]// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 1833-1844. 10.1109/iccvw54120.2021.00210 |
[1] | 李顺勇, 李师毅, 胥瑞, 赵兴旺. 基于自注意力融合的不完整多视图聚类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2696-2703. |
[2] | 任烈弘, 黄铝文, 田旭, 段飞. 基于DFT的频率敏感双分支Transformer多变量长时间序列预测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2739-2746. |
[3] | 秦璟, 秦志光, 李发礼, 彭悦恒. 基于概率稀疏自注意力神经网络的重性抑郁疾患诊断[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2970-2974. |
[4] | 王熙源, 张战成, 徐少康, 张宝成, 罗晓清, 胡伏原. 面向手术导航3D/2D配准的无监督跨域迁移网络[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2911-2918. |
[5] | 李力铤, 华蓓, 贺若舟, 徐况. 基于解耦注意力机制的多变量时序预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2732-2738. |
[6] | 杨航, 李汪根, 张根生, 王志格, 开新. 基于图神经网络的多层信息交互融合算法用于会话推荐[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2719-2725. |
[7] | 潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877. |
[8] | 赵志强, 马培红, 黑新宏. 基于双重注意力机制的人群计数方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2886-2892. |
[9] | 黄云川, 江永全, 黄骏涛, 杨燕. 基于元图同构网络的分子毒性预测[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2964-2969. |
[10] | 薛凯鹏, 徐涛, 廖春节. 融合自监督和多层交叉注意力的多模态情感分析网络[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2387-2392. |
[11] | 汪雨晴, 朱广丽, 段文杰, 李书羽, 周若彤. 基于交互注意力机制的心理咨询文本情感分类模型[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2393-2399. |
[12] | 高鹏淇, 黄鹤鸣, 樊永红. 融合坐标与多头注意力机制的交互语音情感识别[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2400-2406. |
[13] | 陈彤, 杨丰玉, 熊宇, 严荭, 邱福星. 基于多尺度频率通道注意力融合的声纹库构建方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2407-2413. |
[14] | 汪才钦, 周渝皓, 张顺香, 王琰慧, 王小龙. 基于语境增强的新能源汽车投诉文本方面-观点对抽取[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2430-2436. |
[15] | 刘禹含, 吉根林, 张红苹. 基于骨架图与混合注意力的视频行人异常检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2551-2557. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||