Image denoising methods are of fundamental importance in image processing and artificial intelligence systems. In this review, we analyze the traditional and state of the art mathematical models for computational color image denoising. These algorithms are divided into methods that are based on the partial differential equations, low rank, sparse representation and recent developments based on deep learning models. These algorithms also compared in terms of image quality measures. Our analysis and review of the computational color image denoising filters indicate that the convolutional neural networks from the deep learning domain obtain high quality restorations in terms of image quality despite the higher computational complexity.

图像去噪方法在图像处理和人工智能系统中至关重要。在这篇综述中，我们分析了用于计算彩色图像去噪的传统数学模型和最新的数学模型。这些算法分为基于偏微分方程，低秩，稀疏表示和基于深度学习模型的最新发展的方法。这些算法还在图像质量度量方面进行了比较。我们对计算彩色图像降噪过滤器的分析和审查表明，尽管计算复杂度较高，但深度学习领域的卷积神经网络仍能获得高质量的图像恢复。