In supervised learning for image denoising, usually the paired clean images and noisy images are collected or synthesised to train a denoising model. L2 norm loss or other distance functions are used as the objective function for training. It often leads to an over-smooth result with less image details. In this paper, we regard the denoising task as a problem of estimating the posterior distribution of clean images conditioned on noisy images. We apply the idea of diffusion model to realize generative image denoising. According to the noise model in denoising tasks, we redefine the diffusion process such that it is different from the original one. Hence, the sampling of the posterior distribution is a reverse process of dozens of steps from the noisy image. We consider three types of noise model, Gaussian, Gamma and Poisson noise. With the guarantee of theory, we derive a unified strategy for model training. Our method is verified through experiments on three types of noise models and achieves excellent performance.

翻译：在图像去噪的有监督学习中，通常收集或合成成对的干净图像和噪声图像来训练去噪模型，并使用L2范数损失或其他距离函数作为训练目标函数。这往往导致结果过于平滑，图像细节缺失。本文将去噪任务视为在给定噪声图像条件下估计干净图像后验分布的问题，并应用扩散模型的思想实现生成式图像去噪。根据去噪任务中的噪声模型，我们重新定义了扩散过程，使其与原始扩散过程有所不同。因此，后验分布的采样是从噪声图像出发，经过数十步逆向过程完成。我们考虑了三种噪声模型：高斯噪声、伽马噪声和泊松噪声。在理论保障下，我们推导出统一的模型训练策略。通过对三种噪声模型的实验验证，该方法取得了优异性能。