Multiple-degradation video super-resolution with direct inversion of the low-resolution formation model

With the increase of popularity of high and ultra high definition displays, the need to improve the quality of content already obtained at much lower resolutions has grown. Since current video super-resolution methods are trained with a single degradation model (usually bicubic downsampling), they are not robust to mismatch between training and testing degradation models, in which case their performance deteriorates. In this work we propose a new Convolutional Neural Network for video super resolution which is robust to multiple degradation models and uses the pseudo-inverse image formation model as part of the network architecture during training. The experimental validation shows that our approach outperforms current state of the art methods.