基于映射的图像扩散
Mapping-Based Image Diffusion
浏览论文内容
中文总结 AI 辅助
提出一种用于图像增强与去噪的新型张量泛函，结合正则化融入应用与上下文信息，证明其极小值存在性，在非线性图像任务表现优异，去噪性能与最先进PDE方法相当。
中文摘要 AI 辅助
本研究中，我们提出一种新型基于张量的泛函，用于目标图像增强与去噪。通过显式正则化，该公式利用第一性原理融入依赖应用场景与上下文的信息。文献中很少有研究处理同时描述依赖应用信息与去噪问题上下文知识的变分模型。我们证明了极小值的存在性，并给出所提泛函在张量对称性约束、凸性及几何解释方面的结果。我们表明，所提框架在存在非线性函数的应用中表现出色，例如伽马校正和目标值域滤波。我们还研究了一般去噪性能，结果显示其与专用的基于偏微分方程（PDE）的最先进方法表现相当。
英文摘要
In this work, we introduce a novel tensor-based functional for targeted image enhancement and denoising. Via explicit regularization, our formulation incorporates application dependent and contextual information using first principles. Few works in literature treat variational models that describe both application dependent information and contextual knowledge of the denoising problem. We prove the existence of a minimizer and present results on tensor symmetry constraints, convexity, and geometric interpretation of the proposed functional. We show that our framework excels in applications where nonlinear functions are present such as in gamma correction and targeted value range filtering. We also study general denoising performance where we show comparable results to dedicated PDE-based state of the art methods.
发表机构
- Heidelberg University（海德堡大学）
- Linköping University（林雪平大学）
机构由 AI 辅助整理，请以论文原文为准。
