Scholarlink

<p>Image denoising is a fundamental problem in image processing, with the primary objective of eliminating noise while effectively preserving image details and structural features. Recent advances in convolutional neural networks (CNNs) have led to the widespread adoption of deep learning-based denoising methods. However, the representative deep image prior (DIP) exhibits limitations in capturing structural features, resulting in insufficient detail preservation during denoising. To address this issue, we propose a novel denoising model that integrates DIP with anisotropic total variation (ATV) regularization, termed DIP-ATV. In the ATV term, a weighted matrix is introduced to couple the gradient operator, enhancing the regularization term’s ability to characterize local image structures. To decouple the weighted matrix and gradient operator from the <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="13662_2025_3984_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="MATHML"><math> <msup> <mi>ℓ</mi> <mn>1</mn> </msup> </math></EquationSource> <EquationSource Format="TEX">$\ell ^{1}$</EquationSource> </InlineEquation>-norm, we employ the alternating direction method of multipliers (ADMM), decomposing the proposed model into several efficiently solvable subproblems. Experimental results demonstrate that DIP-ATV achieves superior visual quality in qualitative evaluations and outperforms state-of-the-art unsupervised denoising methods in quantitative metrics, including PSNR, SSIM, and LPIPS.</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

DIP-based anisotropic total variation regularization for image denoising

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月19日

查看全文
  • Zhi-Feng Pang,
  • Yi ShangGuan,
  • Fuyang Jiang,
  • Xue-Cheng Tai

摘要

Image denoising is a fundamental problem in image processing, with the primary objective of eliminating noise while effectively preserving image details and structural features. Recent advances in convolutional neural networks (CNNs) have led to the widespread adoption of deep learning-based denoising methods. However, the representative deep image prior (DIP) exhibits limitations in capturing structural features, resulting in insufficient detail preservation during denoising. To address this issue, we propose a novel denoising model that integrates DIP with anisotropic total variation (ATV) regularization, termed DIP-ATV. In the ATV term, a weighted matrix is introduced to couple the gradient operator, enhancing the regularization term’s ability to characterize local image structures. To decouple the weighted matrix and gradient operator from the ℓ 1 $\ell ^{1}$ -norm, we employ the alternating direction method of multipliers (ADMM), decomposing the proposed model into several efficiently solvable subproblems. Experimental results demonstrate that DIP-ATV achieves superior visual quality in qualitative evaluations and outperforms state-of-the-art unsupervised denoising methods in quantitative metrics, including PSNR, SSIM, and LPIPS.