Abstract
State-of-the-art atmospheric turbulence image restoration methods utilize standard image processing tools such as optical flow, lucky region and blind deconvolution to restore the images. While promising results have been reported over the past decade, many of the methods are agnostic to the physical model that generates the distortion. In this paper, we revisit the turbulence restoration problem by analyzing the reference frame generation and the blind deconvolution steps in a typical restoration pipeline. By leveraging tools in large deviation theory, we rigorously prove the minimum number of frames required to generate a reliable reference for both static and dynamic scenes. We discuss how a turbulence agnostic model can lead to potential flaws, and how to configure a simple spatial-temporal non-local weighted averaging method to generate references. For blind deconvolution, we present a new data-driven prior by analyzing the distributions of the point spread functions. We demonstrate how a simple prior can outperform state-of-the-art blind deconvolution methods.
Abstract (translated)
最先进的大气湍流图像恢复方法利用标准的图像处理工具，如光流、幸运区和盲反褶积来恢复图像。虽然在过去十年中已经报道了有希望的结果，但许多方法对产生畸变的物理模型都是不可知论的。本文通过分析典型修复管道中的参考坐标系生成和盲反褶积步骤，重新探讨了湍流恢复问题。通过利用大偏差理论中的工具，我们严格证明了为静态和动态场景生成可靠参考所需的最小帧数。我们讨论了湍流不可知模型如何导致潜在的缺陷，以及如何配置一种简单的时空非局部加权平均方法来生成参考。对于盲反褶积，通过分析点扩散函数的分布，提出了一种新的数据驱动先验算法。我们演示了简单先验如何优于最先进的盲反褶积方法。
URL
https://arxiv.org/abs/1905.07498
