Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Arthur Lecert"'
Publikováno v:
IEEE Access, Vol 11, Pp 84574-84588 (2023)
In this work, we study the restoration of text low-light images with outdoor scenes without ground truth. Until now, approaches in the literature have avoided using the Retinex decomposition model in an unsupervised way or have added constraining pri
Externí odkaz:
https://doaj.org/article/68dbf0e603fb4cdeacd449480be12fe3
Publikováno v:
IEEE International Conference on Image Processing
IEEE International Conference on Image Processing, Oct 2022, Bordeaux, France. pp.1-4
IEEE International Conference on Image Processing, Oct 2022, Bordeaux, France. pp.1-4
International audience; We study unsupervised Retinex decomposition for low light image enhancement. Being an underdetermined problem with infinite solutions, well-suited priors are required to reduce the solution space. In this paper, we analyze the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a0f8abb1c63aad17d283142ef1ee7f71
https://hal.science/hal-03806390/document
https://hal.science/hal-03806390/document