Digital Signal Processing, 104:102801, sep, 2020.
![A single video super-resolution GAN for multiple downsampling operators based on pseudo-inverse image formation models [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex
Paper doi abstract bibtex The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. A large amount of current CNN-based Video Super-Resolution methods are designed and trained to handle a specific degradation operator (e.g., bicubic downsampling) and are not robust to mismatch between training and testing degradation models. This causes their performance to deteriorate in real-life applications. Furthermore, many of them use the Mean-Squared-Error as the only loss during learning, causing the resulting images to be too smooth. In this work we propose a new Convolutional Neural Network for video super resolution which is robust to multiple degradation models. During training, which is performed on a large dataset of scenes with slow and fast motions, it uses the pseudo-inverse image formation model as part of the network architecture in conjunction with perceptual losses and a smoothness constraint that eliminates the artifacts originating from these perceptual losses. The experimental validation shows that our approach outperforms current state-of-the-art methods and is robust to multiple degradations.
@article{Santiago2020,
abstract = {The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. A large amount of current CNN-based Video Super-Resolution methods are designed and trained to handle a specific degradation operator (e.g., bicubic downsampling) and are not robust to mismatch between training and testing degradation models. This causes their performance to deteriorate in real-life applications. Furthermore, many of them use the Mean-Squared-Error as the only loss during learning, causing the resulting images to be too smooth. In this work we propose a new Convolutional Neural Network for video super resolution which is robust to multiple degradation models. During training, which is performed on a large dataset of scenes with slow and fast motions, it uses the pseudo-inverse image formation model as part of the network architecture in conjunction with perceptual losses and a smoothness constraint that eliminates the artifacts originating from these perceptual losses. The experimental validation shows that our approach outperforms current state-of-the-art methods and is robust to multiple degradations.},
archivePrefix = {arXiv},
arxivId = {1907.01399},
author = {L{\'{o}}pez-Tapia, Santiago and Lucas, Alice and Molina, Rafael and Katsaggelos, Aggelos K.},
doi = {10.1016/j.dsp.2020.102801},
eprint = {1907.01399},
issn = {10512004},
journal = {Digital Signal Processing},
keywords = {Convolutional neuronal networks,Generative adversarial networks,Perceptual loss functions,Super-resolution,Video},
month = {sep},
pages = {102801},
title = {{A single video super-resolution GAN for multiple downsampling operators based on pseudo-inverse image formation models}},
url = {https://linkinghub.elsevier.com/retrieve/pii/S1051200420301469},
volume = {104},
year = {2020}
}Downloads: 0