Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations
This addresses image restoration for applications like photography or medical imaging, but it is incremental as it modifies existing networks with a new layer type.
The authors tackled image denoising for salt-and-pepper noise by proposing a convolutional neural network with median layers, which outperformed state-of-the-art methods using limited training data.
We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by the 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 the extremely high-level s&p noise without performing any non-trivial preprocessing tasks, which is different from all the existing literature in s&p noise removal. Experiments show that inserting median layers into a simple fully-convolutional network with the L2 loss significantly boosts the signal-to-noise ratio. Quantitative comparisons testify that our network outperforms the state-of-the-art methods with a limited amount of training data. The source code has been released for public evaluation and use (https://github.com/llmpass/medianDenoise).