Structured image super-resolution network based on improved Transformer

被引：0
|
作者：
Lv X.-D. [1 ]
Li J. [1 ]
Deng Z.-N. [1 ]
Feng H. [1 ]
Cui X.-T. [1 ]
Deng H.-X. [1 ]
机构：
[1] College of Information and Computer, Taiyuan University of Technology, Taiyuan
来源：
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2023年 / 57卷 / 05期
关键词：
convolutional neural network; image super-resolution reconstruction; self-attention; spatial attention; Transformer;
D O I：
10.3785/j.issn.1008-973X.2023.05.002
中图分类号：
学科分类号：
摘要：
Most of existing structural image super-resolution reconstruction algorithms can only solve a specific single type of structural image super-resolution problem. A structural image super-resolution network based on improved Transformer (TransSRNet) was proposed. The network used the self-attention mechanism of Transformer mine a wide range of global information in spatial sequences. A spatial attention unit was built by using the hourglass block structure. The mapping relationship between the low-resolution space and the high-resolution space in the local area was concerned. The structured information in the image mapping process was extracted. The channel attention module was used to fuse the features of the self-attention module and the spatial attention module. The TransSRNet was evaluated on highly-structured CelebA, Helen, TCGA-ESCA and TCGA-COAD datasets. Results of evaluation showed that the TransSRNet model had a better overall performance compared with the super-resolution algorithms. With a upscale factor of 8, the PSNR of the face dataset and the medical image dataset could reach 28.726 and 26.392 dB respectively, and the SSIM could reach 0.844 and 0.881 respectively. © 2023 Zhejiang University. All rights reserved.
引用
收藏
页码：865 / 874+910
相关论文
共 26 条
  • [1] DONG C, LOY C C, HE K, Et al., Learning a deep convolutional network for image super-resolution [C], Proceedings of the European Conference on Computer Vision, pp. 184-199, (2014)
  • [2] LEDIG C, THEIS L, HUSZAR F, Et al., Photo-realistic single image super-resolution using a generative adversarial network [C], Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 105-114, (2017)
  • [3] MA C, RAO Y, CHENG Y, Et al., Structure-preserving super-resolution with gradient guidance [C], Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7766-7775, (2020)
  • [4] ZHANG Y, LI K, LI K, Et al., Residual non-local attention networks for image restoration
  • [5] XU Yong-bing, YUAN Dong, YU Da-bing, Et al., Binocular image super-resolution reconstruction algorithm guided by multiattention mechanism [J], Electronic Measurement Technology, 44, 15, pp. 103-108, (2021)
  • [6] ZHOU E, FAN H, CAO Z, Et al., Learning face hallucination in the wild [C], Proceeding of the Association or the Advancement of Artificial Intelligence, pp. 3871-3877, (2015)
  • [7] LIU H, HAN Z, GUO J, Et al., A noise robust face hallucination framework via cascaded model of deep convolutional networks and manifold learning [C], Proceeding of the IEEE International Conference on Multimedia and Expo, pp. 1-6, (2018)
  • [8] LIU S, XIONG C Y, SHI X D, Et al., Progressive face super-resolution with cascaded recurrent convolutional network [J], Neurocomputing, 449, 8, pp. 357-367, (2021)
  • [9] CHEN Y, TAI Y, LIU X, Et al., FSRNet: end-to-end learning face super-resolution with facial priors [C], Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2492-2501, (2018)
  • [10] ZHANG Y, WU Y, CHEN L., MSFSR: a multi-stage face super-resolution with accurate facial representation via enhanced facial boundaries [C], Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 2120-2129, (2020)
123