TY - GEN
T1 - Multiple-degradation video super-resolution with direct inversion of the low-resolution formation model
AU - Lopez-Tapia, Santiago
AU - Lucas, Alice
AU - Molina, Rafael
AU - Katsaggelos, Aggelos K.
N1 - Funding Information:
This work was supported in part by the Sony 2016 Research Award Program Research Project. The work of SLT and RM was supported by the Spanish Ministry of Economy and Competitiveness through project DPI2016-77869-C2-2-R and the Visiting Scholar program at the University of Granada. SLT received financial support through the Spanish FPU program.
Publisher Copyright:
© 2019 IEEE
PY - 2019/9
Y1 - 2019/9
N2 - 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.
AB - 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.
KW - Convolutional neuronal networks
KW - Image formation
KW - Video Super-resolution
UR - http://www.scopus.com/inward/record.url?scp=85075615973&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075615973&partnerID=8YFLogxK
U2 - 10.23919/EUSIPCO.2019.8902338
DO - 10.23919/EUSIPCO.2019.8902338
M3 - Conference contribution
AN - SCOPUS:85075615973
T3 - European Signal Processing Conference
BT - EUSIPCO 2019 - 27th European Signal Processing Conference
PB - European Signal Processing Conference, EUSIPCO
T2 - 27th European Signal Processing Conference, EUSIPCO 2019
Y2 - 2 September 2019 through 6 September 2019
ER -