TADSRNet: A triple-attention dual-scale residual network for super-resolution image quality assessment

被引:0
|
作者
Xing Quan
Kaibing Zhang
Hui Li
Dandan Fan
Yanting Hu
Jinguang Chen
机构
[1] Xi’an Polytechnic University,School of Electronics and Information
[2] Xi’an Polytechnic University,Shaanxi Key Laboratory of Clothing Intelligence, the School of Computer Science
[3] Xinjiang Medical University,School of Medical Engineering and Technology
来源
Applied Intelligence | 2023年 / 53卷
关键词
No-reference image quality assessment; Attention mechanism; Image super-resolution; Residual connection;
D O I
暂无
中图分类号
学科分类号
摘要
Image super-resolution (SR) has been extensively investigated in recent years. However, due to the absence of trustworthy and precise perceptual quality standards, it is challenging to objectively measure the performance of different SR approaches. In this paper, we propose a novel triple attention dual-scale residual network called TADSRNet for no-reference super-resolution image quality assessment (NR-SRIQA). Firstly, we simulate the human visual system (HVS) and construct a triple attention mechanism to acquire more significant portions of SR images through cross-dimensionality, making it simpler to identify visually sensitive regions. Then a dual-scale convolution module (DSCM) is constructed to capture quality-perceived features at different scales. Furthermore, in order to collect more informative feature representation, a residual connection is added to the network to compensate for perceptual features. Extensive experimental results demonstrate that the proposed TADSRNet can predict visual quality with greater accuracy and better consistency with human perception compared with existing IQA methods. The code will be available at https://github.com/kbzhang0505/TADSRNet.
引用
收藏
页码:26708 / 26724
页数:16
相关论文
共 50 条
  • [1] TADSRNet: A triple-attention dual-scale residual network for super-resolution image quality assessment
    Qua, Xing
    Zhang, Kaibing
    Li, Hui
    Fan, Dandan
    Hu, Yanting
    Chen, Jinguang
    APPLIED INTELLIGENCE, 2023, 53 (22) : 26708 - 26724
  • [2] Improved dual-scale residual network for image super-resolution
    Liu, Huan
    Cao, Feilong
    NEURAL NETWORKS, 2020, 132 : 84 - 95
  • [3] Triple-Attention Mixed-Link Network for Single-Image Super-Resolution
    Cheng, Xi
    Li, Xiang
    Yang, Jian
    APPLIED SCIENCES-BASEL, 2019, 9 (15):
  • [4] Residual scale attention network for arbitrary scale image super-resolution
    Fu, Ying
    Chen, Jian
    Zhang, Tao
    Lin, Yonggang
    NEUROCOMPUTING, 2021, 427 : 201 - 211
  • [5] Face Super-Resolution via Triple-Attention Feature Fusion Network
    Zhao, Kanghui
    Lu, Tao
    Zhang, Yanduo
    Wang, Yu
    Wang, Yuanzhi
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2022, E105A (04) : 748 - 752
  • [6] A Dual-Scale Convolutional Neural Network for Super-Resolution
    Liu, Jing
    He, Shuai
    Xue, Yuxin
    Zhang, Xiaoyan
    THIRTEENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2021), 2021, 11878
  • [7] Polarization Image Super-resolution Reconstruction Based on Dual Attention Residual Network
    Xu Guoming
    Wang Jie
    Ma Jian
    Wang Yong
    Liu Jiaqing
    Li Yi
    ACTA PHOTONICA SINICA, 2022, 51 (04) : 295 - 309
  • [8] Residual shuffle attention network for image super-resolution
    Xuanyi Li
    Zhuhong Shao
    Bicao Li
    Yuanyuan Shang
    Jiasong Wu
    Yuping Duan
    Machine Vision and Applications, 2023, 34
  • [9] Residual shuffle attention network for image super-resolution
    Li, Xuanyi
    Shao, Zhuhong
    Li, Bicao
    Shang, Yuanyuan
    Wu, Jiasong
    Duan, Yuping
    MACHINE VISION AND APPLICATIONS, 2023, 34 (05)
  • [10] Residual shuffle attention network for image super-resolution
    Li, Zhiwei
    Zhang, Yaping
    Yang, Yuwei
    Journal of Physics: Conference Series, 2021, 2025 (01):