{"_id":"rdYyKvQfsn2f73tqk","bibbaseid":"lpeztapia-lucas-molina-katsaggelos-asinglevideosuperresolutionganformultipledownsamplingoperatorsbasedonpseudoinverseimageformationmodels-2020","author_short":["López-Tapia, S.","Lucas, A.","Molina, R.","Katsaggelos, A. K."],"bibdata":{"bibtype":"article","type":"article","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":[{"propositions":[],"lastnames":["López-Tapia"],"firstnames":["Santiago"],"suffixes":[]},{"propositions":[],"lastnames":["Lucas"],"firstnames":["Alice"],"suffixes":[]},{"propositions":[],"lastnames":["Molina"],"firstnames":["Rafael"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]}],"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","bibtex":"@article{Santiago2020,\nabstract = {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.},\narchivePrefix = {arXiv},\narxivId = {1907.01399},\nauthor = {L{\\'{o}}pez-Tapia, Santiago and Lucas, Alice and Molina, Rafael and Katsaggelos, Aggelos K.},\ndoi = {10.1016/j.dsp.2020.102801},\neprint = {1907.01399},\nissn = {10512004},\njournal = {Digital Signal Processing},\nkeywords = {Convolutional neuronal networks,Generative adversarial networks,Perceptual loss functions,Super-resolution,Video},\nmonth = {sep},\npages = {102801},\ntitle = {{A single video super-resolution GAN for multiple downsampling operators based on pseudo-inverse image formation models}},\nurl = {https://linkinghub.elsevier.com/retrieve/pii/S1051200420301469},\nvolume = {104},\nyear = {2020}\n}\n","author_short":["López-Tapia, S.","Lucas, A.","Molina, R.","Katsaggelos, A. K."],"key":"Santiago2020","id":"Santiago2020","bibbaseid":"lpeztapia-lucas-molina-katsaggelos-asinglevideosuperresolutionganformultipledownsamplingoperatorsbasedonpseudoinverseimageformationmodels-2020","role":"author","urls":{"Paper":"https://linkinghub.elsevier.com/retrieve/pii/S1051200420301469"},"keyword":["Convolutional neuronal networks","Generative adversarial networks","Perceptual loss functions","Super-resolution","Video"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","ya2CyA73rpZseyrZ8","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["convolutional neuronal networks","generative adversarial networks","perceptual loss functions","super-resolution","video"],"search_terms":["single","video","super","resolution","gan","multiple","downsampling","operators","based","pseudo","inverse","image","formation","models","lópez-tapia","lucas","molina","katsaggelos"],"title":"A single video super-resolution GAN for multiple downsampling operators based on pseudo-inverse image formation models","year":2020}