基于转置注意力和CNN的图像超分辨率重建网络

doi:10.11996/JG.j.2095-302X.2025010035

图学学报 ›› 2025, Vol. 46 ›› Issue (1): 35-46.DOI: 10.11996/JG.j.2095-302X.2025010035

• 图像处理与计算机视觉 • 上一篇下一篇

基于转置注意力和CNN的图像超分辨率重建网络

陈冠豪(), 徐丹(), 贺康建, 施洪贞, 张浩

云南大学信息学院，云南昆明 650091

收稿日期:2024-07-04 接受日期:2024-10-07 出版日期:2025-02-28 发布日期:2025-02-14
通讯作者:徐丹(1968-)，女，教授，博士。主要研究方向为计算机视觉、图像分析与理解、文化计算等。E-mail：danxu@ynu.edu.cn
第一作者:陈冠豪(1995-)，男，硕士研究生。主要研究方向为计算机视觉。E-mail：chenguanhao@stu.ynu.edu.cn
基金资助:
国家自然科学基金(62162068);国家自然科学基金(62202416)

TSA-SFNet: transpose self-attention and CNN based stereoscopic fusion network for image super-resolution

CHEN Guanhao(), XU Dan(), HE Kangjian, SHI Hongzhen, ZHANG Hao

School of Information Science and Engineering, Yunnan University, Kunming Yunnan 650091

Received:2024-07-04 Accepted:2024-10-07 Published:2025-02-28 Online:2025-02-14
Contact: XU Dan (1968-), professor, Ph.D. Her main research interests cover computer vision, image analysis and understanding, cultural computing, etc. E-mail：danxu@ynu.edu.cn
First author：CHEN Guanhao (1995-), master student. His main research interest covers computer vision. E-mail：chenguanhao@stu.ynu.edu.cn
Supported by:
National Natural Science Foundation of China(62162068);National Natural Science Foundation of China(62202416)

摘要/Abstract

摘要：

基于Transformer的图像超分辨率重建方法近年来表现出了显著的性能。针对现有方法仍然面临诸如高频信息不完全恢复、图像重建时附加像素激活不足、跨窗口信息交互不充分以及由残差连接引起的训练不稳定等挑战，提出了基于转置注意力和CNN的图像超分辨率重建网络(TSA-SFNet)。TSA-SFNet通过调整窗口多头自注意力模块来缓解残差连接引起的振幅问题，并引入通道注意力以激活更多像素进行图像重建。此外，为了加强相邻窗口之间的交互以捕获更多的结构信息，并实现对高频细节更全面的重建，同时引入了重叠窗口注意力和卷积前馈神经网络。在经典的超分辨率任务和真实世界的超分辨率挑战方面对该网络模型进行了定量和定性评估。实验结果表明，TSA-SFNet在5个常用基准数据集上取得了最好的结果，并生成了更为逼真的超分辨率重建图像。

关键词: 图像超分辨率重建, 重叠窗口注意力, 高频信息恢复, 像素激活, 自注意力机制

Abstract:

Transformer-based image super-resolution methods have demonstrated remarkable performance in recent years. Nonetheless, existing approaches encounter challenges such as incomplete recovery of high-frequency information, insufficient activation of additional pixels for image reconstruction, inadequate cross-window information interaction, and training instability caused by residual connections. To address these challenges, the transpose self-attention and CNN based stereoscopic fusion network (TSA-SFNet) was proposed. TSA-SFNet adapted the window multi-head self-attention modules to mitigate amplitude issues caused by residual connections and incorporated channel attention to activate more pixels for image reconstruction. Additionally, to bolster the interaction between adjacent windows for capturing additional structural information and achieving a more comprehensive reconstruction of high-frequency details, overlapping window attention and a convolutional feedforward neural network were introduced. Quantitative and qualitative evaluations of the network model were conducted on classical super-resolution tasks and real-world super-resolution challenges. The experimental results demonstrated that the proposed TSA-SFNet achieved state-of-the-art results on five commonly used benchmark datasets and generated more realistic super-resolution images.

Key words: image super-resolution, overlapping window attentions, high frequency information recovery, pixel activation, self-attention mechanism

中图分类号:

陈冠豪, 徐丹, 贺康建, 施洪贞, 张浩. 基于转置注意力和CNN的图像超分辨率重建网络[J]. 图学学报, 2025, 46(1): 35-46.

CHEN Guanhao, XU Dan, HE Kangjian, SHI Hongzhen, ZHANG Hao. TSA-SFNet: transpose self-attention and CNN based stereoscopic fusion network for image super-resolution[J]. Journal of Graphics, 2025, 46(1): 35-46.

图/表 13

图1 TSA-SFNet和SwinIR之间的性能比较

Fig. 1 Performance comparison between TSA-SFNet and SwinIR ((a) ×2 SR on Urban100 (PSNR); (b) ×2 SR on Urban100 (SSIM); (c) ×4 SR on Urban100 (PSNR); (d) ×4 SR on Urban100 (SSIM))

图2 TSA-SFNet整体架构

Fig. 2 The overall architecture of TSA-SFNet

图3 非重叠窗口划分和重叠窗口划分

Fig. 3 Non-overlapping window partition and overlapping window partition

表1 以SwinIR作为对比，SFB和HCAB消融实验

Table 1 For comparison with SwinIR, ablation experiments on SFB and HCAB were conducted

Method	Scale	Params/M	Set14		Urban100
Method	Scale	Params/M	PSNR/dB	SSIM	PSNR/dB	SSIM
SwinIR	×4	11.9	28.94	0.791 4	27.07	0.816 4
w/o SFB	×4	13.7	29.08	0.793 8	27.43	0.825 0
w/o HCAB	×4	19.7	29.05	0.793 6	27.60	0.828 5
TSA-SFNet-S	×4	10.0	29.05	0.793 2	27.54	0.826 9
TSA-SFNet	×4	21.3	29.10	0.794 2	27.64	0.829 3

表2 以HAT作为对比，SFB和HCAB消融实验

Table 2 For comparison with HAT, ablation experiments on SFB and HCAB were conducted

Method	Scale	Params/M	Set14		Urban100
Method	Scale	Params/M	PSNR/dB	SSIM	PSNR/dB	SSIM
HAT	×4	20.8	29.04	0.793 4	27.47	0.825 8
w/o SFB	×4	20.8	29.07	0.794 2	27.51	0.826 5
w/o HCAB	×4	21.3	29.07	0.794 2	27.63	0.829 1
TSA-SFNet	×4	21.3	29.10	0.794 2	27.64	0.829 3

图4 以SwinIR作为对比，SFB和HCAB消融实验的可视化结果(w/o SFB和w/o HCAB代表将TSA-SFNet中的模块替换成SwinIR对应模块)

Fig. 4 For comparison with SwinIR, the visualized results of the ablation experiments for SFB and HCAB are presented (w/o SFB and w/o HCAB represent the replacement of the corresponding modules in TSA-SFNet with those from SwinIR) ((a) HR; (b) SwinIR; (c) w/o SFB; (d) w/o HCAB; (e) TSA-SFNet)

图5 以HAT作为对比，SFB和HCAB消融实验的可视化结果(w/o SFB和w/o HCAB代表将TSA-SFNet中的模块替换成HAT对应模块)

Fig. 5 For comparison with HAT, the visualized results of the ablation experiments for SFB and HCAB are presented. (w/o SFB and w/o HCAB represent the replacement of the corresponding modules in TSA-SFNet with those from HAT) ((a) HR; (b) HAT; (c) w/o SFB; (d) w/o HCAB; (e) TSA-SFNet)

表3 TSA-SFNet和最先进的超分方法定量比较

Table 3 Quantitative comparison of TSA-SFNet with the state-of-the-art-super-resolution methods

Method	Scale	Years	Set5		Set14		B100		Urban100		Manga109
Method	Scale	Years	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
EDSR	×4	2017	32.46	0.896 8	28.80	0.787 6	27.71	0.742 0	26.64	0.803 3	31.02	0.914 8
RCAN	×4	2018	32.63	0.900 2	28.87	0.788 9	27.77	0.743 6	26.82	0.808 7	31.22	0.917 3
RDN	×4	2018	32.47	0.899 0	28.81	0.787 1	27.72	0.741 9	26.61	0.802 8	31.00	0.915 1
SAN	×4	2019	32.64	0.900 3	28.92	0.788 8	27.78	0.743 6	26.79	0.806 8	31.18	0.916 9
HAN	×4	2020	32.64	0.900 2	28.90	0.789 0	27.80	0.744 2	26.85	0.809 4	31.42	0.917 7
IGNN	×4	2020	32.57	0.899 8	28.85	0.789 1	27.77	0.743 4	26.84	0.809 0	31.28	0.918 2
SwinIR	×4	2021	32.72	0.902 1	28.94	0.791 4	27.83	0.745 9	27.07	0.816 4	31.67	0.922 6
ELAN	×4	2022	32.75	0.902 2	28.96	0.791 4	27.83	0.745 9	27.13	0.816 7	31.68	0.922 6
SRFormer	×4	2023	32.81	0.902 9	29.01	0.791 9	27.85	0.747 2	27.20	0.818 9	31.75	0.923 7
HAT	×4	2023	32.81	0.903 6	29.04	0.793 4	27.91	0.748 7	27.47	0.825 8	32.01	0.925 4
TSA-SFNet	×4	-	32.90	0.903 8	29.10	0.794 2	27.91	0.749 2	27.64	0.829 3	32.07	0.926 1

图6 本文方法TSA-SFNet与最先进的图像超分辨率重建任务上的定性比较结果

Fig. 6 Qualitative comparison of our method TSA-SFNet with the state-of-the-art image super-resolution methods on SR task ((a) HR; (b) Bicubic; (c) EDSR; (d) RCAN; (e) RDN; (f) IGNN; (g) NLSA; (h) SwinIR; (i) HAT; (j) TSA-SFNet (Ours))

图7 本文方法TSA-SFNet与最先进的图像超分辨率重建方法在×4字母超分辨率任务上的定性比较

Fig. 7 Qualitative comparison of our method TSA-SFNet with the state-of-the-art image super-resolution methods on the ×4 letter SR task ((a) HR; (b) NLSA; (c) SwinIR; (d) HAT; (e) TSA-SFNet (Ours))

表4 TSA-SFNet-S和最先进的超分方法定量比较

Table 4 Quantitative comparison of TSA-SFNet-S and state-of-the-art-super-resolution methods

Method	Scale	Params/M	Set5		Set14		B100		Urban100		Manga109
Method	Scale	Params/M	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
EDSR	×4	43.1	32.46	0.896 8	28.80	0.787 6	27.71	0.742 0	26.64	0.803 3	31.02	0.914 8
RCAN	×4	15.6	32.63	0.900 2	28.87	0.788 9	27.77	0.743 6	26.82	0.808 7	31.22	0.917 3
RDN	×4	22.3	32.47	0.899 0	28.81	0.787 1	27.72	0.741 9	26.61	0.802 8	31.00	0.915 1
RNAN	×4	9.3	32.49	0.898 2	28.83	0.787 8	27.72	0.742 1	26.61	0.802 3	31.09	0.914 9
IGNN	×4	49.5	32.57	0.899 8	28.85	0.789 1	27.77	0.743 4	26.84	0.809 0	31.28	0.918 2
NLSA	×4	44.2	32.59	0.900 0	28.87	0.789 1	27.78	0.744 4	26.96	0.810 9	31.27	0.918 4
SwinIR	×4	11.9	32.72	0.902 1	28.94	0.791 4	27.83	0.745 9	27.07	0.816 4	31.67	0.922 6
ELAN	×4	8.3	32.75	0.902 2	28.96	0.791 4	27.83	0.745 9	27.13	0.816 7	31.68	0.922 6
HAT-S	×4	9.6	32.69	0.902 1	29.06	0.792 8	27.89	0.748 1	27.44	0.824 3	31.88	0.924 5
TSA-SFNet-S	×4	10.0	32.79	0.902 8	29.05	0.793 2	27.90	0.748 6	27.54	0.826 9	31.94	0.925 1

图8 本文方法TSA-SFNet-S与最先进的图像超分辨率重建方法在×4超分辨率任务上的定性比较

Fig. 8 Qualitative comparison of our method TSA-SFNet-S with the state-of-the-art image SR methods on the ×4 SR task ((a) HR; (b )Bicubic; (c) EDSR; (d) RCAN; (e) RDN; (f) IGNN; (g) NLSA; (h) SwinIR; (i) HAT; (j) TSA-SFNet-S (Ours))

图9 本文方法TSA-SFNet与最先进的方法在×4真实世界图像超分辨率重建任务上的定性比较

Fig. 9 Qualitative comparison of our method TSA-SFNet with the state-of-the-art methods on the ×4 real-world image SR task ((a) LR; (b) ESRGAN; (c) BSRGAN; (d) Real-ESRGAN; (e) SwinIR; (f) HAT; (g) TSA-SFNet (Ours))

参考文献 60

[1]	DONG C, LOY C C, HE K M, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307. DOI PMID
[2]	DONG C, LOY C C, TANG X O. Accelerating the super-resolution convolutional neural network[C]// The 14th European Conference. Cham: Springer, 2016: 391-407.
[3]	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. New York: IEEE Press, 2016: 1646-1654.
[4]	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. New York: IEEE Press, 2017: 1132-1140.
[5]	ZHANG Y L, LI K P, LI K, et al. Image super-resolution using very deep residual channel attention networks[C]// The 15th European Conference on Computer Vision. Cham: Springer, 2018: 294-310.
[6]	GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.
[7]	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. New York: IEEE Press, 2017: 105-114.
[8]	WANG X T, YU K, WU S X, et al. ESRGAN: enhanced super-resolution generative adversarial networks[C]// European Conference on Computer Vision. Cham: Springer, 2018: 63-79.
[9]	ZHANG K, LIANG J Y, VAN GOOL L, et al. Designing a practical degradation model for deep blind image super-resolution[C]// 2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 4771-4780.
[10]	LIANG J Y, CAO J Z, SUN G L, et al. SwinIR: image restoration using swin transformer[C]// 2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 1833-1844.
[11]	FANG J S, LIN H J, CHEN X Y, et al. A hybrid network of CNN and transformer for lightweight image super-resolution[C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 1102-1111.
[12]	CHEN X Y, WANG X T, ZHOU J T, et al. Activating more pixels in image super-resolution transformer[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2023: 22367-22377.
[13]	ZHANG X D, ZENG H, GUO S, et al. Efficient long-range attention network for image super-resolution[C]// The 17th European Conference on Computer Vision. Cham: Springer, 2022: 649-667.
[14]	ZHOU Y P, LI Z, GUO C L, et al. SRFormer: permuted self-attention for single image super-resolution[C]// 2023 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2023: 12734-12745.
[15]	LIU Z, HU H, LIN Y T, et al. Swin transformer v2: scaling up capacity and resolution[C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 11999-12009.
[16]	PARK N, KIM S. How do vision transformers work?[EB/OL]. [2024-05-04]. https://arxiv.org/abs/2202.06709.
[17]	WANG P H, ZHENG W Q, CHEN T L, et al. Anti-oversmoothing in deep vision transformers via the Fourier domain analysis: from theory to practice[EB/OL]. [2024-05-04]. https://arxiv.org/abs/2203.05962.
[18]	TIMOFTE R, AGUSTSSON E, VAN GOOL L, et al. Ntire 2017 challenge on single image super-resolution: methods and results[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. New York: IEEE Press, 2017: 1110-1121.
[19]	WANG X T, YU K, DONG C, et al. Recovering realistic texture in image super-resolution by deep spatial feature transform[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2018: 606-615.
[20]	GHIFARY M, KLEIJN W B, ZHANG M J, et al. Deep reconstruction-classification networks for unsupervised domain adaptation[C]// The 14th European Conference on Computer Vision. Cham: Springer, 2016: 597-613.
[21]	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. New York: IEEE Press, 2017: 2790-2798.
[22]	WANG X T, XIE L B, DONG C, et al. Real-ESRGAN: training real-world blind super-resolution with pure synthetic data[C]// 2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 1905-1914.
[23]	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. New York: IEEE Press, 2017: 4549-4557.
[24]	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. New York: IEEE Press, 2016: 770-778.
[25]	满开亮, 汪友生, 刘继荣. 基于稠密残差网络的图像超分辨率重建算法[J]. 图学学报, 2021, 42(4): 556-562.
	MAN K L, WANG Y S, LIU J R. Image super-resolution reconstruction algorithm based on dense residual network[J]. Journal of Graphics, 2021, 42(4): 556-562 (in Chinese).
[26]	李彬, 王平, 赵思逸. 基于双重注意力机制的图像超分辨重建算法[J]. 图学学报, 2021, 42(2): 206-215.
	LI B, WANG P, ZHAO S Y. Image super-resolution reconstruction based on dual attention mechanism[J]. Journal of Graphics, 2021, 42(2): 206-215 (in Chinese). DOI
[27]	WANG X L, GIRSHICK R, GUPTA A, et al. Non-local neural networks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2018: 7794-7803.
[28]	MEI Y Q, FAN Y C, ZHOU Y Q. Image super-resolution with non-local sparse attention[C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2021: 3516-3525.
[29]	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. New York: IEEE Press, 2019: 11057-11066.
[30]	ZHOU S C, ZHANG J W, ZUO W M, et al. Cross-scale internal graph neural network for image super-resolution[C]// The 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2020: 295.
[31]	LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]// 2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 9992-10002.
[32]	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers for image recognition at scale[EB/OL]. [2024-05-04]. https://arxiv.org/abs/2010.11929.
[33]	CHU X X, TIAN Z, WANG Y Q, et al. Twins: revisiting the design of spatial attention in vision transformers[C]// The 35th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2021: 716.
[34]	LIU L, OUYANG W L, WANG X G, et al. Deep learning for generic object detection: a survey[J]. International Journal of Computer Vision, 2020, 128(2): 261-318.
[35]	WANG W H, XIE E Z, LI X, et al. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions[C]// 2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 548-558.
[36]	WU B C, XU C F, DAI X L, et al. Visual transformers: token-based image representation and processing for computer vision[EB/OL]. [2024-05-04]. https://arxiv.org/abs/2006.03677.
[37]	RAGHU M, UNTERTHINER T, KORNBLITH S, et al. Do vision transformers see like convolutional neural networks?[C]// The 35th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2021: 927.
[38]	LI K C, WANG Y L, ZHANG J H, et al. UniFormer: unifying convolution and self-attention for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(10): 12581-12600.
[39]	YUAN K, GUO S P, LIU Z W, et al. Incorporating convolution designs into visual transformers[C]// 2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 559-568.
[40]	WANG Z D, CUN X D, BAO J M, et al. Uformer: a GENERAL U-shaped transformer for image restoration[C]// 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2022: 17662-17672.
[41]	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. New York: IEEE Press, 2016: 1874-1883.
[42]	SUNDARARAJAN M, TALY A, YAN Q Q. Axiomatic attribution for deep networks[EB/OL]. [2024-05-24]. https://dl.acm.org/doi/10.5555/3305890.3306024.
[43]	WU H P, XIAO B, CODELLA N, et al. CvT: introducing convolutions to vision transformers[C]// 2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 22-31.
[44]	XIAO T T, SINGH M, MINTUN E, et al. Early convolutions help transformers see better[C]// The 35th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2021: 30392-30400.
[45]	LE BA J, KIROS J R, HINTON G E. Layer normalization[EB/OL]. [2024-05-24]. https://arxiv.org/abs/1607.06450.
[46]	DING M, YANG Z Y, HONG W Y, et al. CogView: mastering text-to-image generation via transformers[EB/OL]. [2024-05-24]. https://proceedings.neurips.cc/paper/2021/hash/a4d92e2cd541fca87e4620aba658316d-Abstract.html.
[47]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// The 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6000-6010.
[48]	IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[EB/OL]. [2024-05-24]. https://dl.acm.org/doi/10.5555/3045118.3045167.
[49]	WU Y X, HE K M. Group normalization[C]// The 15th European Conference on Computer Vision. Cham: Springer, 2018: 3-19.
[50]	PATEL K, BUR A M, LI F J, et al. Aggregating global features into local vision transformer[C]// The 26th International Conference on Pattern Recognition. New York: IEEE Press, 2022: 1141-1147.
[51]	VASWANI A, RAMACHANDRAN P, SRINIVAS A, et al. Scaling local self-attention for parameter efficient visual backbones[C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2021: 12889-12899.
[52]	BEVILACQUA M, ROUMY A, GUILLEMOT C, et al. Low-complexity single-image super-resolution based on nonnegative neighbor embedding[EB/OL]. [2024-05-24]. https://people.rennes.inria.fr/Aline.Roumy/results/SR_BMVC12.html.
[53]	ZEYDE R, ELAD M, PROTTER M. On single image scale-up using sparse-representations[C]// The 7th International Conference on Curves and Surfaces. Cham: Springer, 2012: 711-730.
[54]	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]// The 8th IEEE International Conference on Computer Vision. New York: IEEE Press, 2001: 416-423.
[55]	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. New York: IEEE Press, 2015: 5197-5206.
[56]	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.
[57]	JOHNSON J, ALAHI A, FEI-FEI L. Perceptual losses for real-time style transfer and super-resolution[C]// The 14th European Conference on Computer Vision. Cham: Springer, 2016: 694-711.
[58]	ZHANG Y L, TIAN Y P, KONG Y, et al. Residual dense network for image super-resolution[C]// IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2018: 2472-2481.
[59]	NIU B, WEN W L, REN W Q, et al. Single image super-resolution VIA A holistic attention network[C]// The 16th European Conference on Computer Vision. Cham: Springer, 2020: 191-207.
[60]	ZHANG Y L, LI K P, LI K, et al. Residual non-local attention networks for image restoration[EB/OL]. [2024-05-24]. https://arxiv.org/abs/1903.10082.

基于转置注意力和CNN的图像超分辨率重建网络

TSA-SFNet: transpose self-attention and CNN based stereoscopic fusion network for image super-resolution

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 60

相关文章 5

编辑推荐

Metrics

本文评价

[1]	苑朝, 赵明雪, 张丰羿, 冯晓勇, 李冰, 陈瑞. 基于点云特征增强的复杂室内场景3D目标检测[J]. 图学学报, 2025, 46(1): 59-69.
[2]	彭文, 林金炜. 基于空间信息关注和纹理增强的短小染色体分类方法[J]. 图学学报, 2024, 45(5): 1017-1029.
[3]	刘宗明, 洪唯, 龙睿, 祝越, 张小宇. 基于自注意机制的乳源瑶绣自动生成与应用研究[J]. 图学学报, 2024, 45(5): 1096-1105.
[4]	常东良 , 尹军辉 , 谢吉洋 , 孙维亚 , 马占宇 . 面向图像分类的基于注意力引导的 Dropout[J]. 图学学报, 2021, 42(1): 32-36.
[5]	张永鹏, 张春梅, 白静. 基于 DenseNet-Attention 模型的高光谱图像分类[J]. 图学学报, 2020, 41(6): 897-904.