Plug-and-Play optimization recently emerged as a powerful technique for solving inverse problems by plugging a denoiser into a classical optimization algorithm. The denoiser accounts for the regularization and therefore implicitly determines the prior knowledge on the data, hence replacing typical handcrafted priors. In this paper, we extend the concept of plug-and-play optimization to use denoisers that can be parameterized for non-constant noise variance. In that aim, we introduce a preconditioning of the ADMM algorithm, which mathematically justifies the use of such an adjustable denoiser. We additionally propose a procedure for training a convolutional neural network for high quality non-blind image denoising that also allows for pixel-wise control of the noise standard deviation. We show that our pixel-wise adjustable denoiser, along with a suitable preconditioning strategy, can further improve the plug-and-play ADMM approach for several applications, including image completion, interpolation, demosaicing and Poisson denoising.
翻译:插图和插图优化最近作为一种强大的技术,通过将解密器插入古典优化算法来解决反向问题。 解译器对正规化进行了核算, 从而隐含地决定了先前的数据知识, 从而取代了典型的手工制作的前科。 在本文中, 我们扩展插图和编程优化的概念, 以使用可以对非连续噪音差异进行参数化的隐隐含器。 在这方面, 我们引入了ADMM算法的先决条件, 该算法在数学上证明使用这种可调整的解密器是有道理的。 我们还提议了一个程序, 用于培训一个高品质的非盲图像解密的革命神经网络, 从而也允许对噪音标准偏离进行像素一样的控制。 我们表明,我们的像素明智的可调整脱色器, 加上一个合适的先决条件战略, 可以进一步改进包括图像完成、 内插图、 解和 Poisson 解译在内的多个应用程序的插图和剧 ADMM方法。