BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv6.5.6//EN
X-ORIGINAL-URL:https://cmc.deusto.eus/
X-WR-CALNAME:cmc.deusto.eus
X-WR-CALDESC:DeustoCCM - Chair of Computational Mathematics at University of Deusto
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-ad1b74292d67078dfb12d20eeca2566e@cmc.deusto.eus
DTSTART:20210707T110000Z
DTEND:20210707T120000Z
DTSTAMP:20251031T214000Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:Learning Energy-Based Models for Image Reconstruction
DESCRIPTION:Speaker: Prof. Dr. Alexander Effland\nAffiliation: University of Bonn, Germany\nOrganized by: FAU DCN-AvH, Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship at FAU Erlangen-Nürnberg (Germany)\nATTENDING THIS TALK\nZoom link\nMeeting ID: 615 2629 5822 | PIN code: 150498\nAbstract. Various problems in computer vision and medical imaging can be cast as inverse problems.\nA frequent method for solving inverse problems is the variational approach, which amounts to minimizing an energy composed of a data fidelity term and a regularizer.\nClassically, handcrafted regularizers are used, which are commonly outperformed by state-of-the-art deep learning approaches.\nIn this talk, we combine the variational formulation of inverse problems with deep learning by introducing the data-driven general-purpose total deep variation regularizer.\nMoreover, we introduce the novel concept of shared prior learning to account for training in the absence of ground truth images.\nWe achieve state-of-the-art results for several imaging tasks.\n
URL:https://cmc.deusto.eus/events-calendar/learning-energy-based-models-for-image-reconstruction/
CATEGORIES:FAU DCN-AvH Seminar,Seminar/Talk
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/FAUDCNSeminar-07jul2021-AEfflandPM.png
END:VEVENT
END:VCALENDAR