Zobrazeno 1 - 10
of 83
pro vyhledávání: '"Andrés Almansa"'
Publikováno v:
Computational Visual Media, Vol 5, Iss 3, Pp 267-291 (2019)
Abstract We present a system for the removal of objects from videos. As input, the system only needs a user to draw a few strokes on the first frame, roughly delimiting the objects to be removed. To the best of our knowledge, this is the first system
Externí odkaz:
https://doaj.org/article/73a7b7f46e8b4e8f80ba20b8d5fd0747
Publikováno v:
Image Processing On Line, Vol 3, Pp 242-251 (2013)
In most typical digital cameras, even high-end digital single lens reflex ones (DSLR), the acquired images are sampled at rates below the Nyquist critical rate, causing aliasing effects. In this work we describe a new algorithm for the estimation of
Externí odkaz:
https://doaj.org/article/cef39696bde6448a8872647a254583e2
Publikováno v:
Image Processing On Line, Vol 2, Pp 8-21 (2012)
Externí odkaz:
https://doaj.org/article/505fa2a286f24e8bba2b8c6c620cd558
Autor:
Carlos Graziani, Andrés Almansa
Publikováno v:
Estudios Económicos, Vol 13, Iss 1 (1998)
Se presenta un procedimiento para la simulación de: modelos lineales, en tiempo continuo, con previsión perfecta e histéresis. El procedimiento, que constituye la base del algoritmo LPFH, parte de una generalización de la forma estructural están
Externí odkaz:
https://doaj.org/article/0b6cbe2766934072a4995afc439d6592
Autor:
Rémi Laumont, Valentin De Bortoli, Andrés Almansa, Julie Delon, Alain Durmus, Marcelo Pereyra
Publikováno v:
Journal of Mathematical Imaging and Vision
Journal of Mathematical Imaging and Vision, 2023, 65, pp.140-163. ⟨10.1007/s10851-022-01134-7⟩
Journal of Mathematical Imaging and Vision, 2023, 65, pp.140-163. ⟨10.1007/s10851-022-01134-7⟩
International audience; Bayesian methods to solve imaging inverse problems usually combine an explicit data likelihood function with a prior distribution that explicitly models expected properties of the solution. Many kinds of priors have been explo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e16589f8ee7a2daf93a9607a478f6257
Publikováno v:
SSRN Electronic Journal.
Autor:
Rémi Laumont, Valentin De Bortoli, Andrés Almansa, Julie Delon, Alain Durmus, Marcelo Pereyra
Publikováno v:
SIAM Journal on Imaging Sciences
SIAM Journal on Imaging Sciences, Society for Industrial and Applied Mathematics, 2022
SIAM Journal on Imaging Sciences, 2022, ⟨10.1137/21m1406349⟩
SIAM Journal on Imaging Sciences, Society for Industrial and Applied Mathematics, 2022
SIAM Journal on Imaging Sciences, 2022, ⟨10.1137/21m1406349⟩
Since the seminal work of Venkatakrishnan et al. [83] in 2013, Plug & Play (PnP) methods have become ubiquitous in Bayesian imaging. These methods derive Minimum Mean Square Error (MMSE) or Maximum A Posteriori (MAP) estimators for inverse problems i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fe08476ef653b12aabef7584e120e96b
https://hal.archives-ouvertes.fr/hal-03161400v2/file/main(1).pdf
https://hal.archives-ouvertes.fr/hal-03161400v2/file/main(1).pdf
In this work we address the problem of solving ill-posed inverse problems in imaging where the prior is a variational autoencoder (VAE). Specifically we consider the decoupled case where the prior is trained once and can be reused for many different
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::69f2c97a7e2a918e14fffe3db1b11919
https://hal.archives-ouvertes.fr/hal-03151455v2/document
https://hal.archives-ouvertes.fr/hal-03151455v2/document
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030755485
SSVM
SSVM
In this work, we propose a framework to learn a local regularization model for solving general image restoration problems. This regularizer is defined with a fully convolutional neural network that sees the image through a receptive field correspondi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b75d233a167ea130df13a2fb2b06cb38
https://doi.org/10.1007/978-3-030-75549-2_29
https://doi.org/10.1007/978-3-030-75549-2_29
Autor:
Marcela Carvalho, Pauline Trouvé-Peloux, Frédéric Champagnat, Bertrand Le Saux, Andrés Almansa
Publikováno v:
IEEE Geoscience and Remote Sensing Letters
IEEE Geoscience and Remote Sensing Letters, IEEE-Institute of Electrical and Electronics Engineers, 2019, ⟨10.1109/LGRS.2019.2947783⟩
IEEE Geoscience and Remote Sensing Letters, IEEE-Institute of Electrical and Electronics Engineers, 2019, ⟨10.1109/LGRS.2019.2947783⟩
Aerial or satellite imagery is a great source for land surface analysis, which might yield land use maps or elevation models. In this investigation, we present a neural network framework for learning semantics and local height together. We show how t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::299910689dc57393e7c856c839fe9d72
https://hal.archives-ouvertes.fr/hal-02386074v2/file/DTIS19229.1580910909_postprint.pdf
https://hal.archives-ouvertes.fr/hal-02386074v2/file/DTIS19229.1580910909_postprint.pdf