Distribution Conditional Denoising: A Flexible Discriminative Image Denoiser
This work provides an incremental improvement in image denoising for computer vision practitioners by offering a more flexible model that handles multiple noise types and levels.
This paper introduces a flexible discriminative image denoiser that uses multi-task learning on a U-Net based FCN. The model achieves state-of-the-art performance for images corrupted with Gaussian and Poisson noise and can generalize a fixed noise level denoiser to various noise levels.
A flexible discriminative image denoiser is introduced in which multi-task learning methods are applied to a densoising FCN based on U-Net. The activations of the U-Net model are modified by affine transforms that are a learned function of conditioning inputs. The learning procedure for multiple noise types and levels involves applying a distribution of noise parameters during training to the conditioning inputs, with the same noise parameters applied to a noise generating layer at the input (similar to the approach taken in a denoising autoencoder). It is shown that this flexible denoising model achieves state of the art performance on images corrupted with Gaussian and Poisson noise. It has also been shown that this conditional training method can generalise a fixed noise level U-Net denoiser to a variety of noise levels.