Convolutional neural network with median layers for denoising salt-and-pepper contaminations

We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by salt-and-pepper (s&p) noise. A median layer simply performs median filtering on all feature channels. By adding this kind of layer into some widely used fully convolutional deep neural networks, we develop an end-to-end network that removes extremely high-level s&p noise without performing any non-trivial preprocessing tasks. Experiments show that inserting median layers into a simple fully-convolutional network with the L₂ loss significantly boosts signal-to-noise ratio. Quantitative comparisons testify that our network outperforms the state-of-the-art methods with a limited amount of training data.