用近似方法加速深度图像先验求解，实现大图去模糊
Fast Inexact Bilevel Optimization for Analytical Deep Image Priors
- 采用自适应不精确双层优化，避免逐次精确求解底层问题
- 在2D彩色图像去模糊任务中实现显著提速，支持更大规模图像
- 适合需要高效图像重建的科研与工业应用
Dittmer等人（2020）提出的解析型深度图像先验（ADP）通过双层优化建立了深度图像先验与经典正则化理论之间的联系。然而，若要求底层问题精确求解，计算成本极高。为此，本文提出采用自适应不精确双层优化来求解ADP问题。我们拓展了Salehi等人（2024）提出的不精确双层下降法，使其适用于ADP框架所需的无穷维设置。数值实验表明，该方法带来的计算加速使ADP可应用于此前文献无法处理的大规模问题，例如2D彩色图像去模糊。
原文摘要 · Abstract (English)
The analytical deep image prior (ADP) introduced by Dittmer et al. (2020) establishes a link between deep image priors and classical regularization theory via bilevel optimization. While this is an elegant construction, it involves expensive computations if the lower-level problem is to be solved accurately. To overcome this issue, we propose to use adaptive inexact bilevel optimization to solve ADP problems. We discuss an extension of a recent inexact bilevel method called the method of adaptive inexact descent of Salehi et al.(2024) to an infinite-dimensional setting required by the ADP framework. In our numerical experiments we demonstrate that the computational speed-up achieved by adaptive inexact bilevel optimization allows one to use ADP on larger-scale problems than in the previous literature, e.g. in deblurring of 2D color images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。