Super-Resolution Using Deep Convolutional Networks

This is a project about Neural Networks for Data Science course implementing a state-of-the-art architecture from a given scientific paper (see [1]). More specifically, we will construct the Robust-UNet architecture aiming to improve the resolution of an input images using a particular dataset.

Results:

Below some of our results:

References:

[1] Hu, Xiaodan, et al. "RUNet: A Robust UNet Architecture for Image Super-Resolution." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2019

Authors:

Francesco Russo, Michele Cernigliaro, Iason Tsardanidis