BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:From motion capture of interacting hands to video based rendering.
  - Luca Ballan\, Institute of Visual Computing in ETH Zurich
DTSTART:20121204T140000Z
DTEND:20121204T150000Z
UID:TALK41769@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:The talk will be structured in two parts.\nI will first talk a
 bout my research on marker-less motion capture\, in particular presenting 
 my recent ECCV work on hands tracking. Capturing the motion of hands inter
 acting with each other and with an object is a challenging task due to the
  large number of degrees of freedom\, self-occlusions\, and similarity bet
 ween the fingers. I will show how we addressed this problem by proposing a
  generative approach modeling all the elements of the scene as a unique ar
 ticulated deformable object\, and exploiting some discriminatively learnt 
 features.\nIn the second part\, I will talk about my research on interacti
 ve free-viewpoint video. I will show how it is possible to navigate a coll
 ection of videos representing an event casually captured by people in the 
 audience. Instead of recovering a perfect 3D representation of the recorde
 d scene\, which in general is very challenging\, I will propose several si
 mplifying assumptions allowing video based rendering in such a scenario.\n
 I will also show a live real-time demo of the proposed interactive navigat
 ion tool on different video collections.\nURLs:\nhttp://cvg.ethz.ch/resear
 ch/ih-mocap/\nhttp://cvg.ethz.ch/research/unstructured-vbr/\nhttp://www.in
 f.ethz.ch/personal/lballan/
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR