Diffusion Model for Generative Image Denoising
This addresses the problem of over-smoothing in image denoising for computer vision applications, but it is incremental as it adapts existing diffusion models to denoising tasks.
The paper tackles image denoising by framing it as estimating the posterior distribution of clean images given noisy ones, using a redefined diffusion model approach, and achieves excellent performance across Gaussian, Gamma, and Poisson noise models.
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.