Journal of Infrared and Millimeter Waves, Volume. 44, Issue 3, 431(2025)

Sparsity and self-similarity priors guided deep learning for blind image super-resolution

Sun-Yi GE1,2,3, Xiao-Wei LUO3, Shi-Yang FENG1,2, and Bin WANG1,2、*
Author Affiliations
  • 1Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University,Shanghai 200433, China
  • 2Image and Intelligence Laboratory, School of Information Science and Technology, Fudan University,Shanghai 200433, China
  • 3Media Technology Resources Department, UNISOC (Shanghai)Technologies Co. Ltd,Shanghai 200120, China
  • show less

    The existing deep learning-based image blind super-resolution algorithms only utilize neural networks to learn the end-to-end mapping from low-resolution (LR) images to high-resolution (HR) images, only allowing the network to implicitly learn image priors, resulting in algorithms that still produce blurry super-resolution results. To address the above issues, a deep learning image blind super-resolution algorithm guided by sparsity and self-similarity priors is proposed. Initially, for various LR image inputs, a dynamic linear kernel estimation module is employed to effectively estimate the corresponding blur kernels; Subsequently, a deep unfolding deconvolution filtering module based on the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) is utilized to explicitly model the sparsity prior of signal, achieving deconvolution restoration of the degraded images; Finally, a dual-path multi-scale large receptive field restoration module leverages the self-similarity prior of images for super-resolution recovery. The experimental results indicate that, compared to existing methods, the proposed algorithm achieves a peak signal-to-noise ratio (PSNR) of 31.66 and a structural similarity index (SSIM) of 0.8725 on the publicly available Gaussian8 dataset, and attains a PSNR of 29.08 and an SSIM of 0.8007 on the DIV2KRK dataset. The images restored by the proposed algorithm not only exhibit the highest restoration metrics but also superior visual quality.

    Keywords
    Tools

    Get Citation

    Copy Citation Text

    Sun-Yi GE, Xiao-Wei LUO, Shi-Yang FENG, Bin WANG. Sparsity and self-similarity priors guided deep learning for blind image super-resolution[J]. Journal of Infrared and Millimeter Waves, 2025, 44(3): 431

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Interdisciplinary Research on Infrared Science

    Received: Oct. 22, 2024

    Accepted: --

    Published Online: Jul. 9, 2025

    The Author Email: Bin WANG (wangbin@fudan.edu.cn)

    DOI:10.11972/j.issn.1001-9014.2025.03.013

    Topics