Výsledky vyhledávání - "Hoang Trieu Vy Le"

The faster proximal algorithm, the better unfolded deep learning architecture ? The study case of image denoising

Autor: Hoang Trieu Vy Le, Nelly Pustelnik, Marion Foare

Deep learning has revolutionized many image processing tasks such as classification or segmentation and, more recently, gives very promising results for solving inverse problems. It however remains a gap between the deep learning blackbox approaches

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9b54a10b480d9a38eef7b2b3109293c
https://hal.science/hal-03864637

Zobrazit plný text záznamu

Proximal Based Strategies for Solving Discrete Mumford-Shah With Ambrosio-Tortorelli Penalization on Edges

Autor: Hoang Trieu Vy Le, Marion Foare, Nelly Pustelnik

Publikováno v: IEEE Signal Processing Letters
IEEE Signal Processing Letters, 2022

International audience; This work is dedicated to joint image restoration and contour detection considering the Ambrosio-Tortorelli functional. Two proximal alternating minimization schemes with convergence guarantees are provided, PALM-AT and SL-PAM

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::911fdda0ecd491c00d1a209b738b2219
https://hal.science/hal-03381093/file/SPL.pdf

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání