El Helou Majed, Susstrunk Sabine
IEEE Trans Image Process. 2020 Mar 4. doi: 10.1109/TIP.2020.2976814.
Blind and universal image denoising consists of using a unique model that denoises images with any level of noise. It is especially practical as noise levels do not need to be known when the model is developed or at test time. We propose a theoretically-grounded blind and universal deep learning image denoiser for additive Gaussian noise removal. Our network is based on an optimal denoising solution, which we call fusion denoising. It is derived theoretically with a Gaussian image prior assumption. Synthetic experiments show our network's generalization strength to unseen additive noise levels. We also adapt the fusion denoising network architecture for image denoising on real images. Our approach improves real-world grayscale additive image denoising PSNR results for training noise levels and further on noise levels not seen during training. It also improves state-of-the-art color image denoising performance on every single noise level, by an average of 0.1dB, whether trained on or not.
盲态通用图像去噪是指使用一个独特的模型对任何噪声水平的图像进行去噪。这在实际应用中非常实用，因为在开发模型或测试时不需要知道噪声水平。我们提出了一种基于理论的盲态通用深度学习图像去噪器，用于去除加性高斯噪声。我们的网络基于一种最优去噪解决方案，我们称之为融合去噪。它是在高斯图像先验假设的基础上从理论上推导出来的。合成实验表明了我们的网络对未见过的加性噪声水平的泛化能力。我们还将融合去噪网络架构应用于真实图像的去噪。我们的方法提高了训练噪声水平以及训练中未见过的噪声水平下真实世界灰度加性图像去噪的PSNR结果。无论是否经过训练，它还在每个噪声水平上提高了当前最优的彩色图像去噪性能，平均提高了0.1dB。
