Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Santiago Lopez-Tapia"'
Publikováno v:
IEEE Access, Vol 12, Pp 127368-127379 (2024)
This paper presents a novel variational deep-learning approach for video atmospheric turbulence correction. We modify and tailor the Nonlinear Activation Free Network (NAFNet) architecture for video restoration, introducing a new transformer-based ch
Externí odkaz:
https://doaj.org/article/8903b41a58e14a24961ffa4daa917979
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 29:2580-2589
Passive millimeter wave images (PMMWIs) can be used to detect and localize objects concealed under clothing. Unfortunately, the quality of the acquired images and the unknown position, shape, and size of the hidden objects render these tasks challeng
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::10cea2bc84eddc40aa66a2b052810846
https://doi.org/10.1109/tcsvt.2017.2774927
https://doi.org/10.1109/tcsvt.2017.2774927
Publikováno v:
EUSIPCO
Despite the success of Recurrent Neural Networks in tasks involving temporal video processing, few works in Video Super-Resolution (VSR) have employed them. In this work we propose a new Gated Recurrent Convolutional Neural Network for VSR adapting s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::10af93cbf2804179ded861d6903e2f3c
https://doi.org/10.23919/eusipco47968.2020.9287713
https://doi.org/10.23919/eusipco47968.2020.9287713
Publikováno v:
Digital Signal Processing. 119:103285
In recent years, deep learning-based models have gained momentum in imaging problems such as image and video super-resolution, image restoration or inpainting. The analytical approaches that have traditionally been used to solve image inverse problem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3eefd86279f1bd465617cf6792633332
https://doi.org/10.1016/j.dsp.2021.103285
https://doi.org/10.1016/j.dsp.2021.103285
Autor:
Neelanshi Varia, Liliana Sydorenko, Mitchell Reed Smith, Minzi Wang, Jennifer B. Dunn, Aggelos K. Katsaggelos, Pablo Ruiz, Jeffrey W. Matthews, Yuanzhe Jin, Bradley Zercher, Santiago Lopez-Tapia
Publikováno v:
International Journal of Applied Earth Observation and Geoinformation. 105:102581
Wetlands serve many important ecosystem services, yet the United States lacks up-to-date, high-resolution wetland inventories. New, automated techniques for developing wetland segmentation maps from high-resolution aerial imagery can improve our unde
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c4fa4fdd73bf2ca2808b3f8d0484ee4
https://doi.org/10.1016/j.jag.2021.102581
https://doi.org/10.1016/j.jag.2021.102581
Publikováno v:
ICIP
While high and ultra high definition displays are becoming popular, most of the available content has been acquired at much lower resolutions. In this work we propose to pseudo-invert with regularization the image formation model using GANs and perce
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c74545b319f1026720f7820b99dc80d3
https://doi.org/10.1109/icip.2019.8803709
https://doi.org/10.1109/icip.2019.8803709
Publikováno v:
ICIP
While Deep Neural Networks trained for solving inverse imaging problems (such as super-resolution, denoising, or inpainting tasks) regularly achieve new state-of-the-art restoration performance, this increase in performance is often accompanied with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7fa00853c25c61bf6f091503bec572c8
https://doi.org/10.1109/icip.2019.8803715
https://doi.org/10.1109/icip.2019.8803715
Autor:
Aggelos K. Katsaggelos, Alice Lucas, Santiago Lopez-Tapia, Yul Hee Kim, Rafael Molina, Xijun Wang, Xinyi Wu
Publikováno v:
EUSIPCO
Semantic information is widely used in the deep learning literature to improve the performance of visual media processing. In this work, we propose a semantic prior based Generative Adversarial Network (GAN) model for video super-resolution. The mode
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5bfdac9a1a65db344ba311df088ec9be
https://doi.org/10.23919/eusipco.2019.8902987
https://doi.org/10.23919/eusipco.2019.8902987
Publikováno v:
EUSIPCO
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 degrad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::664f02243168f6a08b2f298eeebf1f4b
https://doi.org/10.23919/eusipco.2019.8902338
https://doi.org/10.23919/eusipco.2019.8902338
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
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bfe31412af922c38cd25f3fcd251a8e6
http://arxiv.org/abs/1907.01399
http://arxiv.org/abs/1907.01399
