Luis Carranza |
Thu 11 Feb 2016, 12:45 - 13:45 |
4.31/33 |
If you have a question about this talk, please contact: Steph Smith (ssmith32)
In this talk we show how the classic problem of stereo matching using global optimization can be improved by using a cost function that combines both pixel wise and block matching costs, modifying the smoothness term, including information about surface direction, and optimally assigning a plane per pixel.