BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:1153@cran.univ-lorraine.fr
DTSTART;TZID=Europe/Paris:20251120T150000
DTEND;TZID=Europe/Paris:20251120T180000
DTSTAMP:20251112T192202Z
URL:https://www.cran.univ-lorraine.fr/events/soutenance-de-these-de-ricard
 o-espinosa-loera/
SUMMARY:Soutenance de thèse de Ricardo Espinosa-Loera
DESCRIPTION:Title: Deep-learning based image exposure correction and depth 
 estimation for 3D cartography in endoscopy\n\nAbstract:\nThis thesis inves
 tigates the application of deep learning techniques to improve 3D reconstr
 uction in endoscopy. A passive vision framework is proposed to enhance mon
 ocular video data by means of photometric correction and self-supervised d
 epth estimation\, addressing challenges related to uneven illumination and
  limited geometric information. The contributions include the development 
 of Endo4IE\, a synthetic dataset specifically designed to support the trai
 ning of exposure correction models\, as well as the implementation of deep
 -learning methods capable of recovering structural details in poorly illum
 inated regions. In addition\, an illumination-invariant and self-supervise
 d depth estimation model is introduced to infer scene geometry from monocu
 lar sequences without requiring ground-truths. These modules have been int
 egrated into a 3D reconstruction pipeline enabling the generation of dense
  surfaces with coherent shapes. Extensive experiments on both synthetic an
 d real colonoscopic data demonstrate significant improvements in i) the im
 age contrasts\, ii) the accuracy of the 3D camera trajectory tracking\, an
 d iii) the quality of the surface construction. These results all contribu
 te to a more reliable and geometry-aware visualization in clinical endosco
 py.\n \nJury Composition:\n  Rapporteurs:\n  David Fofi\, PU\, Université
  de Bourgogne\, Laboratoire ImViA\n  Jean-Bernard Hayet\, CIMAT\, Guanajua
 to\, Mexico\n\n  Examiners:\n  Mariel Alfaro-Ponce\, Tecnológico de Monte
 rrey\, Campus Mexico City\n  Marie-Odile Berger\, Directrice de Recherche 
 INRIA\, LORIA\n\n  Thesis Co-directors:\n  Christian Daul\, PU\, Universit
 é de Lorraine\, CRAN\n  Gilberto Ochoa-Ruiz\, Tecnológico de Monterrey\,
  Campus Guadalajara\n\nTeams link: click here\n
CATEGORIES:Soutenances thèses et HDR
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20251026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR