Dense ByNet: Residual Dense Network for Image Super-Resolution
This paper proposes a method, Dense ByNet, for single image super-resolution based on a convolutional neural network (CNN). The main innovation is a new architecture that combines several CNN design choices. Using a residual network as a basis, it introduces dense connections inside residual blocks, significantly reducing the number of parameters. Second, we apply dilation convolutions to increase the spatial context. Lastly, we propose modifications to the activation and cost functions. We evaluate the method on benchmark datasets and show that it achieves state-of-the-art results over multiple upscaling factors in terms of peak SNR and structural similarity (SSIM).