Unsupervised Image Denoising with Score Function
This work addresses denoising for images with complex noise, which is an incremental improvement for applications in computer vision and image processing.
The paper tackles the problem of single image denoising under complex noise models by proposing a new unsupervised approach based on score functions, achieving good performance in complicated cases where other methods fail.
Though achieving excellent performance in some cases, current unsupervised learning methods for single image denoising usually have constraints in applications. In this paper, we propose a new approach which is more general and applicable to complicated noise models. Utilizing the property of score function, the gradient of logarithmic probability, we define a solving system for denoising. Once the score function of noisy images has been estimated, the denoised result can be obtained through the solving system. Our approach can be applied to multiple noise models, such as the mixture of multiplicative and additive noise combined with structured correlation. Experimental results show that our method is comparable when the noise model is simple, and has good performance in complicated cases where other methods are not applicable or perform poorly.