Compressive Learning of Deep Regularization for Denoising

Autor: Hui Shi, Yann Traonmilin, Jean-François Aujol

Publikováno v: Lecture Notes in Computer Science ISBN: 9783031319747

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0eb31fe62c8aa48e4cf1de83b19d7197
https://doi.org/10.1007/978-3-031-31975-4_13

Sketched learning for image denoising

Autor: Jean-François Aujol, Yann Traonmilin, Hui Shi

Publikováno v: The Eighth International Conference on Scale Space and Variational Methods in Computer Vision (SSVM)
The Eighth International Conference on Scale Space and Variational Methods in Computer Vision (SSVM), May 2021, Cabourg, France
Lecture Notes in Computer Science ISBN: 9783030755485
SSVM

International audience; The Expected Patch Log-Likelihood algorithm (EPLL) and its extensions have shown good performances for image denoising. It estimates a Gaussian mixture model (GMM) from a training database of image patches and it uses the GMM

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6221ecf9f2f6cb51ccb0d6cea76da983
https://hal.archives-ouvertes.fr/hal-03123805

Learning Defects in Old Movies from Manually Assisted Restoration

Autor: Jean-François Aujol, Jean-Denis Durou, Arthur Renaudeau, François Lauze, Travis Seng, Fabien Pierre, Axel Carlier

Publikováno v: ICPR 2020-25th International Conference on Pattern Recognition
ICPR 2020-25th International Conference on Pattern Recognition, Sep 2020, Milan / Virtual, Italy
ICPR

International audience; We propose to detect defects in old movies, as the first step of a larger framework of old movies restoration by inpainting techniques. The specificity of our work is to learn a film restorer's expertise from a pair of sequenc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b14c857805cfbfd80e6ddaceed7ebcfa
https://hal.archives-ouvertes.fr/hal-02965296/file/ARTHUR_ICPR_2020.pdf

Projected gradient descent for non-convex sparse spike estimation

Autor: Jean-François Aujol, Yann Traonmilin, Arthur Leclaire

Publikováno v: IEEE Signal Processing Letters
IEEE Signal Processing Letters, Institute of Electrical and Electronics Engineers, 2020
IEEE Signal Processing Letters, Institute of Electrical and Electronics Engineers, 2020, 27, pp.1110-1114. ⟨10.1109/LSP.2020.3003241⟩

International audience; We propose a new algorithm for sparse spike estimation from Fourier measurements. Based on theoretical results on non-convex optimization techniques for off-the-grid sparse spike estimation, we present a projected gradient des

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::adeab624b03b6981f4a11c54a9174d4b
https://hal.archives-ouvertes.fr/hal-02311624v2/document

Normal Integration: A Survey

Autor: Yvain Quéau, Jean-Denis Durou, Jean-François Aujol

Publikováno v: Journal of Mathematical Imaging and Vision
Journal of Mathematical Imaging and Vision, Springer Verlag, 2018, 60 (4), pp.576-593. ⟨10.1007/s10851-017-0773-x⟩

International audience; The need for efficient normal integration methods is driven by several computer vision tasks such as shape-from-shading, photometric stereo, deflectometry. In the first part of this survey, we select the most important propert

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ab4f97c96ba2a33a1ba83869e4387f3e
https://doi.org/10.1007/s10851-017-0773-x