BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine Learning Techniques for 3D Registration with Images - Prof
 essor Vincent Lepetit of Graz University of Technology\, Austria
DTSTART:20160201T153000Z
DTEND:20160201T173000Z
UID:TALK64250@talks.cam.ac.uk
CONTACT:Geraldine Duggan
DESCRIPTION:Professor Lepetit will present 3 recent works that rely on sta
 tistical learning\, and mostly deep learning\, for 3D registration. The fi
 rst work introduces a novel representation of 3D parts that is well adapte
 d to the 3D registration of textureless\, possible occluded objects. The s
 econd part will present a method that learns how to detect feature points 
 stable to drastic light changes. The third one shows how to train a feedba
 ck loop end-to-end to register the 3D pose of a hand using depth maps. Thi
 s last method is currently the best performing one on hand pose benchmarks
 .\n
LOCATION:Cambridge University Engineering Department\, LT2
END:VEVENT
END:VCALENDAR