BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Comparative Study on the Loss Functions for Image Enhancement Ne
 tworks - Aamir Mustafa\, University of Cambridge
DTSTART:20220630T130000Z
DTEND:20220630T140000Z
UID:TALK176321@talks.cam.ac.uk
CONTACT:104848
DESCRIPTION:Image enhancement and image retouching processes are often dom
 inated by global (shift-invariant) change of colour and tones. Most "deep 
 learning" based methods proposed for image enhancement are trained to enfo
 rce similarity in pixel values and/or in the high-level feature space. We 
 hypothesise that for tasks\, such as image enhancement and retouching\, wh
 ich involve a significant shift in colour statistics\, training the model 
 to restore the overall colour distribution can be of vital importance. To 
 address this\, we study the effect of a Histogram Matching loss function o
 n a state-of-the art colour enhancement network - HDRNet. The loss enforce
 s similarity of the RGB histograms of the predicted and the target images.
  By providing detailed qualitative and quantitative comparison of differen
 t loss functions on varied datasets\, we conclude that enforcing similarit
 y in the colour distribution achieves substantial improvement in performan
 ce and can play a significant role while choosing loss functions for image
  enhancement networks.
LOCATION:William Gates Building\, Level 2 (Rainbow Corridor)\, Seminar Roo
 m: SS03
END:VEVENT
END:VCALENDAR