BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards User-Friendly Image Inpainting: Learning-to-Rank based Ima
 ge Quality Assessment for Image Inpainting - Mariko Isogawa (NTT Media Int
 elligence Laboratories) 
DTSTART:20170908T100000Z
DTEND:20170908T110000Z
UID:TALK79791@talks.cam.ac.uk
CONTACT:54031
DESCRIPTION:\nImage inpainting\, which removes and restores unwanted regio
 ns in images\, is widely acknowledged as a task whose results vary largely
  depending on the parameter settings. In typical use cases\, users have to
  choose parameters and observe the results by trial and error\, until the 
 desired results are obtained. Thus a way to automatically select the best 
 result is needed.\nIn this talk\, I will introduce our current research fo
 r learning based image quality assessment (IQA) methods for inpainting to 
 support this need. Our framework uses no subjectively annotated data\; we 
 use only simulated failure results of inpainted images whose subjective qu
 alities are controlled as the training data.\n\n
LOCATION:CBL Room BE-438\, Department of Engineering
END:VEVENT
END:VCALENDAR