Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning
This addresses the problem of denoising images without prior knowledge of noise levels for practitioners in image processing, though it is incremental as it builds on existing denoising methods.
The paper tackles blind and universal image denoising for additive Gaussian noise by proposing a theoretically-grounded deep learning model based on fusion denoising, which improves state-of-the-art color image denoising by an average of 0.1dB across all noise levels.
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.