PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Automatic foreground-background refocusing
Alexander Loktyushin and Stefan Harmeling
In: ICIP 2011(2011).


A challenging problem in image restoration is to recover an im- age with a blurry foreground. Such images can easily occur with modern cameras, when the auto-focus aims mistakenly at the back- ground (which will appear sharp) instead of the foreground, where usually the object of interest is. In this paper we propose an auto- matic procedure that (i) estimates the amount of out-of-focus blur, (ii) segments the image into foreground and background incorpo- rating clues from the blurriness, (iii) recovers the sharp foreground, and finally (iv) blurs the background to refocus the scene. On several real photographs with blurry foreground and sharp background, we demonstrate the effectiveness and limitations of our method.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:9308
Deposited By:Stefan Harmeling
Deposited On:16 March 2012