What is important in an image?

Supervisor(s):Prof. Ayellet Tal
Abstract:

Given an image, parts of it attract our immediate attention – these are the important, or the “salient”, parts. A fundamental challenge in computer vision is the detection of the salient pixels automatically. In the attached image, these are the white areas. New 3D cameras pose a new challenge – given a set of of points, can we detect the salient points automatically? In this project we wish to study the relation between the two problems: 2D saliency detection that is based on colors and 3D saliency detection that is based on geometry.