Graph algorithms for more efficient inference in 1st-order and higher-order MRF's

Add to your list(s) Download to your calendar using vCal

• Professor Ramin Zabih, Cornell University
• Tuesday 11 August 2015, 14:00-15:00
• Engineering Department - Lecture Room - LR4.

If you have a question about this talk, please contact dsu21.

Efficient inference is a major challenge for the MRF ’s that arise in computer vision. Most such MRF ’s are 1st-order, and are typically solved with methods like message passing or graph cuts. I will present a new preprocessing technique for 1st-order MRF ’s that makes widely used graph cut methods an order of magnitude more efficient. Higher-order MRF ’s are very powerful, but present a much more difficult challenge; I will describe techniques based on a variant of submodular flow that can perform efficient inference over some important higher-order priors.

This talk is part of the dsu21's list series.

This talk is included in these lists:

• Engineering Department - Lecture Room - LR4

Note that ex-directory lists are not shown.