Scholarlink

<p>Image deblurring is a challenging inverse problem due to its ill-posed nature, leading to various strategies for enhancing stability. The Rudin-Osher-Fatemi (ROF) model is a seminal framework recognized for its effectiveness in image denoising and deblurring, inspiring numerous variational techniques. Despite existing approaches focusing on solving analysis-based, synthesis-based, and balanced models, achieving a more accurate solution to the ROF model remains an open question. The Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) is a widely applied numerical algorithm known for its efficiency in large-scale optimization. However, FISTA’s effectiveness in solving the ROF model is constrained because it is primarily designed for synthesis models when the sparsifying transform is orthonormal. To overcome this limitation, we propose a novel Kernel FISTA (K-FISTA), integrated with a structured Pseudoinverse Image Formulation (PIF) model. In practice, our approach outperforms classical methods like ADMM and sPADMM by achieving lower final energy values, offering a more accurate numerical approximation to the common minimizer while maintaining fast convergence. Extensive experiments validate the effectiveness of the K-FISTA method in image deblurring, and we provide theoretical guarantees for its convergence.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Kernel FISTA and Application to Image Deblurring

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月5日

查看全文
  • Te Qi,
  • Hao Zhang,
  • Zeyu Li,
  • Yingying Fang,
  • Tieyong Zeng

摘要

Image deblurring is a challenging inverse problem due to its ill-posed nature, leading to various strategies for enhancing stability. The Rudin-Osher-Fatemi (ROF) model is a seminal framework recognized for its effectiveness in image denoising and deblurring, inspiring numerous variational techniques. Despite existing approaches focusing on solving analysis-based, synthesis-based, and balanced models, achieving a more accurate solution to the ROF model remains an open question. The Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) is a widely applied numerical algorithm known for its efficiency in large-scale optimization. However, FISTA’s effectiveness in solving the ROF model is constrained because it is primarily designed for synthesis models when the sparsifying transform is orthonormal. To overcome this limitation, we propose a novel Kernel FISTA (K-FISTA), integrated with a structured Pseudoinverse Image Formulation (PIF) model. In practice, our approach outperforms classical methods like ADMM and sPADMM by achieving lower final energy values, offering a more accurate numerical approximation to the common minimizer while maintaining fast convergence. Extensive experiments validate the effectiveness of the K-FISTA method in image deblurring, and we provide theoretical guarantees for its convergence.