BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Nuclear-norm Model for Multi-Frame Super-resolution Reconstructi
 on - Raymond Chan (Chinese University of Hong Kong)
DTSTART:20171103T111000Z
DTEND:20171103T120000Z
UID:TALK94426@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:In this talk\, we give a new variational approach to obtain su
 per-resolution images from multiple low-resolution image frames extracted 
 from video clips. First the displacement between the low-resolution frames
  and the reference frame are computed by an optical flow algorithm. The di
 splacement matrix is then decomposed into product of two matrices correspo
 nding to the integer and fractional displacement matrices respectively. Th
 e integer displacement matrices give rise to a non-convex low-rank prior w
 hich is then convexified to give the nuclear-norm regularization term. By 
 adding a standard 2-norm data fidelity term to it\, we obtain our proposed
  nuclear-norm model. Alternating direction method of multipliers can then 
 be used to solve the model. Comparison of our method with other models on 
 synthetic and real video clips shows that our resulting images are more ac
 curate with less artifacts. It also provides much finer and discernable de
 tails.  Joint work with Rui Zhao. Research supported by HKRGC.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR