Super-Resolution Reconstruction of Texture Image Based on Mixed-Scale Non-Local Attention

被引：0
|
作者：
Yao P. [1 ]
Wei Y. [1 ]
Lu H. [1 ]
Wang S. [1 ]
机构：
[1] School of Control and Computer Engineering, North China Electric Power University, Beijing
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2023年 / 35卷 / 10期
关键词：
attention mechanism; non-local attention; single image super-resolution; texture image;
D O I：
10.3724/SP.J.1089.2023.19488
中图分类号：
学科分类号：
摘要：
Compared with ordinary images, the local detail of texture images has a small scale while high density, which may lose high-frequency details at low-resolution, thus affecting the effect of super-resolution image reconstruction. To solve this problem, we presented a super-resolution method for texture images using Mixed-Scale Non-Local Attention (MSNLA). Firstly, we proposed Equal-Scale Non-Local attention (ESNLA) based on Cross-Scale Non-Local Attention (CSNLA) to extract the high-frequency information of equal-scale similar feature blocks in the whole image. Besides, considering that deploying parallelized non-local attention modules will bring heavy computational burden and will increase the number of parameters, we proposed a parameter sharing method that combined CSNLA and ESNLA, namely MSNLA. Secondly, we fused the similar feature of different scales generated by MSNLA into the input feature map using channel projection. Finally, we combined the features extracted by MSNLA for super-resolution reconstruction using non-local feature fusion. Experimental results on Describable Texture Dataset (DTD) demonstrate that our proposed algorithm improve the PSNR by 0.16 dB while reducing the number of model parameters by about 10.3% with better visual effect. © 2023 Institute of Computing Technology. All rights reserved.
引用
收藏
页码：1479 / 1488
页数：9
相关论文
共 28 条
  • [1] Greenspan H., Super-resolution in medical imaging, The Computer Journal, 52, 1, pp. 43-63, (2008)
  • [2] Shi Jun, Wang Linlin, Wang Shanshan, Et al., Applications of deep learning in medical imaging: a survey, Journal of Image and Graphics, 25, 10, pp. 1953-1981, (2020)
  • [3] Zhong Jiusheng, Jiang Nan, Hu Bin, Et al., A super-resolution model and algorithm of remote sensing image based on sparse representation, Acta Geodaetica et Cartographica Sinica, 43, 3, pp. 276-283, (2014)
  • [4] Rasti P, Uiboupin T, Escalera S, Et al., Convolutional neural network super resolution for face recognition in surveillance monitoring, Proceedings of International Conference on Articulated Motion and Deformable Objects, pp. 175-184, (2016)
  • [5] Liu Ying, Zhu Li, Lim Kengpang, Et al., Review and prospect of image super-resolution technology, Journal of Frontiers of Computer Science and Technology, 14, 2, pp. 181-199, (2020)
  • [6] Mei Y Q, Fan Y C, Zhou Y Q, Et al., Image super-resolution with cross-scale non-local attention and exhaustive self-exemplars mining, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5689-5698, (2020)
  • [7] Lim B, Son S, Kim H, Et al., Enhanced deep residual networks for single image super-resolution, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1132-1140, (2017)
  • [8] Zhang Y L, Li K P, Li K, Et al., Image super-resolution using very deep residual channel attention networks, Proceedings of the 15th European Conference on Computer Vision, pp. 294-310, (2018)
  • [9] Wang Yanran, Luo Yuhao, Yin Dong, A super resolution technology of face image for surveillance video, Acta Optica Sinica, 37, 3, pp. 112-119, (2017)
  • [10] Keys R., Cubic convolution interpolation for digital image processing, IEEE Transactions on Acoustics, Speech, and Signal Processing, 29, 6, pp. 1153-1160, (1981)
123