An Attention-Based Approach for Single Image Super Resolution

被引:0
|
作者
Liu, Yuan [1 ,2 ,3 ]
Wang, Yuancheng [1 ]
Li, Nan [1 ]
Cheng, Xu [4 ]
Zhang, Yifeng [1 ,2 ,3 ]
Huang, Yongming [1 ]
Lu, Guojun [5 ]
机构
[1] Southeast Univ, Sch Informat Sci & Engn, Nanjing 210096, Jiangsu, Peoples R China
[2] Nanjing Inst Commun Technol, Nanjing 211100, Jiangsu, Peoples R China
[3] Nanjing Univ, State Key Lab Novel Software Technol, Nanjing 210093, Jiangsu, Peoples R China
[4] Southeast Univ, Sch Automat, Nanjing 210096, Jiangsu, Peoples R China
[5] Federat Univ Australia, Fac Sci & Technol, Melbourne, Vic, Australia
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The main challenge of single image super resolution (SISR) is the recovery of high frequency details such as tiny textures. However, most of the state-of-the-art methods lack specific modules to identify high frequency areas, causing the output image to be blurred. We propose an attention-based approach to give a discrimination between texture areas and smooth areas. After the positions of high frequency details are located, high frequency compensation is carried out. This approach can incorporate with previously proposed SISR networks. By providing high frequency enhancement, better performance and visual effect are achieved. We also propose our own SISR network composed of DenseRes blocks. The block provides an effective way to combine the low level features and high level features. Extensive benchmark evaluation shows that our proposed method achieves significant improvement over the state-of-the-art works in SISR.
引用
收藏
页码:2777 / 2784
页数:8
相关论文
共 50 条
  • [31] Improving Single-Image Super-Resolution with Dilated Attention
    Zhang, Xinyu
    Cheng, Boyuan
    Yang, Xiaosong
    Xiao, Zhidong
    Zhang, Jianjun
    You, Lihua
    [J]. ELECTRONICS, 2024, 13 (12)
  • [32] GRAN: ghost residual attention network for single image super resolution
    Axi Niu
    Pei Wang
    Yu Zhu
    Jinqiu Sun
    Qingsen Yan
    Yanning Zhang
    [J]. Multimedia Tools and Applications, 2024, 83 : 28505 - 28522
  • [33] Fused pyramid attention network for single image super-resolution
    Chen, Shi
    Bi, Xiuping
    Zhang, Lefei
    [J]. IET IMAGE PROCESSING, 2023, 17 (06) : 1681 - 1693
  • [34] Learning Dynamic Generative Attention for Single Image Super-Resolution
    Chen, Rui
    Zhang, Yan
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (12) : 8368 - 8382
  • [35] Efficient residual attention network for single image super-resolution
    Fangwei Hao
    Taiping Zhang
    Linchang Zhao
    Yuanyan Tang
    [J]. Applied Intelligence, 2022, 52 : 652 - 661
  • [36] Single image super-resolution via a ternary attention network
    Lianping Yang
    Jian Tang
    Ben Niu
    Haoyue Fu
    Hegui Zhu
    Wuming Jiang
    Xin Wang
    [J]. Applied Intelligence, 2023, 53 : 13067 - 13081
  • [37] Feedback Pyramid Attention Networks for Single Image Super-Resolution
    Wu, Huapeng
    Gui, Jie
    Zhang, Jun
    Kwok, James T.
    Wei, Zhihui
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 33 (09) : 4881 - 4892
  • [38] Dual residual attention module network for single image super resolution
    Wang, Xiumei
    Gu, Yanan
    Gao, Xinbo
    Hui, Zheng
    [J]. NEUROCOMPUTING, 2019, 364 : 269 - 279
  • [39] CANS: Combined Attention Network for Single Image Super-Resolution
    Muhammad, Wazir
    Aramvith, Supavadee
    Onoye, Takao
    [J]. IEEE Access, 2024, 12 : 167498 - 167517
  • [40] GRAN: ghost residual attention network for single image super resolution
    Niu, Axi
    Wang, Pei
    Zhu, Yu
    Sun, Jinqiu
    Yan, Qingsen
    Zhang, Yanning
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (10) : 28505 - 28522