BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Geometry and learning in 3D correspondence problems - Alex Bronste
 in ()
DTSTART:20171214T113000Z
DTEND:20171214T123000Z
UID:TALK96631@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:The need to compute correspondence between three-dimensional o
 bjects is a fundamental ingredient in numerous computer vision and graphic
 s tasks. In this talk\, I will show how several geometric notions related 
 to the Laplacian spectrum provide a set of tools for efficiently calculati
 ng correspondence between deformable shapes. I will also show how this fra
 mework combined with recent ideas in deep learning promises to bring corre
 spondence problems to new levels of accuracy.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR