arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.06085cs.CV
收藏

基于块的图像先验中的合成与分析

Synthesis versus analysis in patch-based image priors

Instituto Superior Técnico, University of Lisbon(里斯本大学高等理工学院)

Mario A. T. Figueiredo

摘要:

在全局模型/先验(例如,使用小波框架)中,在信号/图像先验的制定方式中存在众所周知的分析与合成二分法。在基于块的图像模型/先验中,这种二分法也存在于如何对每个块进行建模的选择中。本文表明,有另一个分析与合成二分法,在整个图像是如何相关的补丁,以及所有现有的基于补丁的配方,提供了一个全球性的图像之前属于分析类别。然后,我们提出了一个合成配方,其中的图像被明确建模为合成添加组合的独立补丁的集合。我们正式确定,这些分析和合成制剂在一般情况下是不等同的,并且这两种制剂在贴剂水平上与分析和合成制剂相容。最后,我们提出了一个例子的交替方向的乘法器(ADMM),可用于执行图像去噪下建议的合成配方,显示其计算的可行性。而不是显示的综合或分析配方的优越性,本文的贡献是建立两种选择的存在,从而关闭相应的差距,在该领域的补丁为基础的图像处理。

英文摘要:

In global models/priors (for example, using wavelet frames), there is a well known analysis vs synthesis dichotomy in the way signal/image priors are formulated. In patch-based image models/priors, this dichotomy is also present in the choice of how each patch is modeled. This paper shows that there is another analysis vs synthesis dichotomy, in terms of how the whole image is related to the patches, and that all existing patch-based formulations that provide a global image prior belong to the analysis category. We then propose a synthesis formulation, where the image is explicitly modeled as being synthesized by additively combining a collection of independent patches. We formally establish that these analysis and synthesis formulations are not equivalent in general and that both formulations are compatible with analysis and synthesis formulations at the patch level. Finally, we present an instance of the alternating direction method of multipliers (ADMM) that can be used to perform image denoising under the proposed synthesis formulation, showing its computational feasibility. Rather than showing the superiority of the synthesis or analysis formulations, the contributions of this paper is to establish the existence of both alternatives, thus closing the corresponding gap in the field of patch-based image processing.

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。

↑