Infrared Image Super-Resolution via Lightweight Information Split Network

被引:3
|
作者
Liu, Shijie [1 ]
Yan, Kang [1 ]
Qin, Feiwei [1 ]
Wang, Changmiao [2 ]
Ge, Ruiquan [1 ]
Zhang, Kai [3 ]
Huang, Jie [4 ]
Peng, Yong [1 ]
Cao, Jin [5 ]
机构
[1] Hangzhou Dianzi Univ, Sch Comp Sci & Technol, Hangzhou, Peoples R China
[2] Shenzhen Res Inst Big Data, Shenzhen, Peoples R China
[3] Swiss Fed Inst Technol, CVL, Zurich, Switzerland
[4] Zhejiang Univ Sci & Technol, Sch Informat & Elect Engn, Hangzhou, Peoples R China
[5] Johns Hopkins Univ, Whiting Sch Engn, Baltimore, MD USA
来源
ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT VIII, ICIC 2024 | 2024年 / 14869卷
关键词
Infrared Image; Super-Resolution; Deep Learning; Lightweight Network;
D O I
10.1007/978-981-97-5603-2_24
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Single image super-resolution (SR) is an established pixel-level vision task aimed at reconstructing a high-resolution image from its degraded low resolution counterpart. Despite the notable advancements achieved by leveraging deep neural networks for SR, most existing deep learning architectures feature an extensive number of layers, leading to high computational complexity and substantial memory demands. To mitigate these challenges, we introduce a novel, efficient, and precise single infrared image SR model, termed the Lightweight Information Split Network (LISN). The LISN comprises four main components: shallow feature extraction, deep feature extraction, dense feature fusion, and high-resolution infrared image reconstruction. A key innovation within this model is the introduction of the Lightweight Information Split Block (LISB) for deep feature extraction. The LISB employs a sequential process to extract hierarchical features, which are then aggregated based on the relevance of the features under consideration. By integrating channel splitting and shift operations, the LISB successfully strikes an optimal balance between enhanced SR performance and a lightweight framework. Comprehensive experimental evaluations reveal that the proposed LISN achieves superior performance over contemporary state-of-the-art methods in terms of both SR quality and model complexity, affirming its efficacy for practical deployment in resource-constrained infrared imaging applications.
引用
收藏
页码:293 / 304
页数:12
相关论文
共 50 条
  • [41] A Hybrid Network of CNN and Transformer for Lightweight Image Super-Resolution
    Fang, Jinsheng
    Lin, Hanjiang
    Chen, Xinyu
    Zeng, Kun
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 1102 - 1111
  • [42] Lightweight adaptive weighted network for single image super-resolution
    Li, Zheng
    Wang, Chaofeng
    Wang, Jun
    Ying, Shihui
    Shi, Jun
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2021, 211
  • [43] Partial convolution residual network for lightweight image super-resolution
    Zhang, Long
    Wan, Yi
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (11) : 8019 - 8030
  • [44] Lightweight image super-resolution with the adaptive weight learning network
    Zhang Y.
    Cheng P.
    Zhang S.
    Wang X.
    Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University, 2021, 48 (05): : 15 - 22
  • [45] Lightweight image super-resolution with a feature-refined network
    Liu, Feiqiang
    Yang, Xiaomin
    De Baets, Bernard
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2023, 111
  • [46] Partial convolutional reparameterization network for lightweight image super-resolution
    Zhang, Long
    Wan, Yi
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2024, 21 (06)
  • [47] Lightweight Progressive Residual Clique Network for Image Super-Resolution
    Huang, Baojin
    He, Zheng
    Wang, Zhongyuan
    Jiang, Kui
    Wang, Guangcheng
    2020 IEEE 32ND INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI), 2020, : 767 - 772
  • [48] A Residual Network with Efficient Transformer for Lightweight Image Super-Resolution
    Yan, Fengqi
    Li, Shaokun
    Zhou, Zhiguo
    Shi, Yonggang
    ELECTRONICS, 2024, 13 (01)
  • [49] Lightweight and Accurate Recursive Fractal Network for Image Super-Resolution
    Li, Juncheng
    Yuan, Yiting
    Mei, Kangfu
    Fang, Faming
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 3814 - 3823
  • [50] A lightweight generative adversarial network for single image super-resolution
    Xinbiao Lu
    Xupeng Xie
    Chunlin Ye
    Hao Xing
    Zecheng Liu
    Changchun Cai
    The Visual Computer, 2024, 40 : 41 - 52