arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.15635cs.ITcs.CVcs.LGeess.IVmath.ITstat.APstat.ML
收藏

用于在散斑噪声存在下恢复图像的 Bagged 深度图像先验

Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise

Rutgers University(罗格斯大学);Columbia University(哥伦比亚大学);University of Maryland(马里兰大学)

Xi Chen, Zhewen Hou, Christopher A. Metzler, Arian Maleki, Shirin Jalali

AI总结:

本文提出 Bagged-DIP 方法并结合投影梯度下降与 Newton-Schulz 算法,用于从散斑噪声多视测量中恢复复值信号,同时建立了深度图像先验下最大似然估计 MSE 的首个理论上界,实现了最先进性能。

摘要:

我们研究了基于似然的方法在理论和算法方面的特性,这些方法用于从多组测量值(称为视数)中恢复受散斑(乘性)噪声影响的复值信号。我们的理论贡献包括建立了在深度图像先验假设下最大似然估计器均方误差(MSE)的首个现有理论上界。我们的理论结果刻画了 MSE 对深度图像先验中参数数量、视数、信号维度以及每视测量数量的依赖关系。在算法方面,我们引入了 Bagged 深度图像先验(Bagged-DIP)的概念,并将其与投影梯度下降相结合。此外,我们展示了在 PGD 迭代过程中采用 Newton-Schulz 算法计算矩阵逆如何降低算法的计算复杂度。我们将证明该方法达到了最先进的性能。

英文摘要:

We investigate both the theoretical and algorithmic aspects of likelihood-based methods for recovering a complex-valued signal from multiple sets of measurements, referred to as looks, affected by speckle (multiplicative) noise. Our theoretical contributions include establishing the first existing theoretical upper bound on the Mean Squared Error (MSE) of the maximum likelihood estimator under the deep image prior hypothesis. Our theoretical results capture the dependence of MSE upon the number of parameters in the deep image prior, the number of looks, the signal dimension, and the number of measurements per look. On the algorithmic side, we introduce the concept of bagged Deep Image Priors (Bagged-DIP) and integrate them with projected gradient descent. Furthermore, we show how employing Newton-Schulz algorithm for calculating matrix inverses within the iterations of PGD reduces the computational complexity of the algorithm. We will show that this method achieves the state-of-the-art performance.

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。

↑