The Image Super-Resolution Algorithm Based on the Dense Space Attention Network

被引:6
|
作者
Duanmu, Chunjiang [1 ]
Zhu, Junjie [1 ]
机构
[1] Zhejiang Normal Univ, Dept Phys & Elect Informat Engn, Jinhua 321004, Zhejiang, Peoples R China
关键词
Feature extraction; Convolution; Spatial resolution; Machine learning; Image edge detection; Image reconstruction; Deep learning; image processing; single image super-resolution; convolution neural network;
D O I
10.1109/ACCESS.2020.3013401
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The deep learning technique has been recently used in the image super-resolution. When the deep learning network is too deep, it is difficult to train this network to make it converge. Furthermore, the problem of gradient loss occurs for a very deep network, which makes the gradient at front layers go to zero, and thus it is impossible to train these layers. Current deep learning in image super-resolution has the following two shortcomings. One is that the features of each convolutional layer are not fully utilized. The other is that the low-resolution input features, containing rich low-frequency information, are treated equally for each channel, and not well utilized. Therefore, a DSAB (dense spatial attention block) is proposed as a basic structure for the network. The features extracted from a DSAB can be treated as a feature matrix. All the feature matrices extracted through the DSABs are concated in the row direction, and are then the inputs for a convolution layer with the kernel size of 3 by 3. The whole network of the proposed algorithm is then given and described in details. The implementation details of the algorithm is then described. The data set of DIV2K, which contains 900 high-resolution images, is used for training of the network. The test images are from Set5 and Set14, as in other papers. Experimental results show that the proposed network model is better than several other representative methods, and the edges of the reconstructed image are clearer and sharper.
引用
收藏
页码:140599 / 140606
页数:8
相关论文
共 50 条
  • [1] Pyramid Attention Dense Network for Image Super-Resolution
    Chen, Si-Bao
    Hu, Chao
    Luo, Bin
    Ding, Chris H. Q.
    Huang, Shi-Lei
    [J]. 2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [2] Stratified attention dense network for image super-resolution
    Zhiwei Liu
    Xiaofeng Mao
    Ji Huang
    Menghan Gan
    Yueyuan Zhang
    [J]. Signal, Image and Video Processing, 2022, 16 : 715 - 722
  • [3] Stratified attention dense network for image super-resolution
    Liu, Zhiwei
    Mao, Xiaofeng
    Huang, Ji
    Gan, Menghan
    Zhang, Yueyuan
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2022, 16 (03) : 715 - 722
  • [4] A Novel Attention Enhanced Dense Network for Image Super-Resolution
    Niu, Zhong-Han
    Zhou, Yang-Hao
    Yang, Yu-Bin
    Fan, Jian-Cong
    [J]. MULTIMEDIA MODELING (MMM 2020), PT I, 2020, 11961 : 568 - 580
  • [5] Dense Hybrid Attention Network for Palmprint Image Super-Resolution
    Wang, Yao
    Fei, Lunke
    Zhao, Shuping
    Zhu, Qi
    Wen, Jie
    Jia, Wei
    Rida, Imad
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2024, 54 (04): : 2590 - 2602
  • [6] Nested Dense Attention Network for Single Image Super-Resolution
    Qiu, Cheng
    Yao, Yirong
    Du, Yuntao
    [J]. PROCEEDINGS OF THE 2021 INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL (ICMR '21), 2021, : 250 - 258
  • [7] Image super-resolution based on residually dense distilled attention network q
    Dun, Yujie
    Da, Zongyang
    Yang, Shuai
    Qian, Xueming
    [J]. NEUROCOMPUTING, 2021, 443 : 47 - 57
  • [8] Remote Sensing Image Super-Resolution Based on Dense Channel Attention Network
    Ma, Yunchuan
    Lv, Pengyuan
    Liu, Hao
    Sun, Xuehong
    Zhong, Yanfei
    [J]. REMOTE SENSING, 2021, 13 (15)
  • [9] Image Super-Resolution Based on Dense Convolutional Network
    Li, Jie
    Zhou, Yue
    [J]. PATTERN RECOGNITION AND COMPUTER VISION, PT II, 2018, 11257 : 134 - 145
  • [10] A Single Image Super-Resolution Algorithm Based on Dense Residual Convolutional Network
    Liu Chengming
    Duan Junyi
    Pang Haibo
    [J]. Pattern Recognition and Image Analysis, 2021, 31 : 1 - 6