arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.08613cs.CVmath.OC
收藏

面向图像逆问题的公平原始对偶分裂方法

Fair Primal Dual Splitting Method for Image Inverse Problems

Beihang University(北京航空航天大学);LMIB;School of Mathematical Sciences(数学科学学院)

Yunfei Qu, Deren Han

AI总结:

针对图像逆问题对应的三函数复合优化问题,提出将光滑项同时纳入原始与对偶子问题的公平原始对偶框架,证明其收敛性与速率,实验显示该方法在图像去噪、超分任务上优于现有SOTA方法。

摘要:

图像逆问题在图像处理、超分辨率和计算机视觉等图像科学重要领域有大量应用,这类应用模型可被视为三函数复合优化问题,可通过多种原始对偶类方法求解。我们提出一种公平原始对偶算法框架,该框架不仅将光滑项纳入原始子问题,还将其纳入对偶子问题。我们统一了所提公平原始对偶方法的全局收敛性并建立了收敛速率。在图像去噪和超分辨率重建上的实验表明,该方法优于当前最先进的方法。

英文摘要:

Image inverse problems have numerous applications, including image processing, super-resolution, and computer vision, which are important areas in image science. These application models can be seen as a three-function composite optimization problem solvable by a variety of primal dual-type methods. We propose a fair primal dual algorithmic framework that incorporates the smooth term not only into the primal subproblem but also into the dual subproblem. We unify the global convergence and establish the convergence rates of our proposed fair primal dual method. Experiments on image denoising and super-resolution reconstruction demonstrate the superiority of the proposed method over the current state-of-the-art.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑