University of Cambridge > Talks.cam > dsu21's list > Graph algorithms for more efficient inference in 1st-order and higher-order MRF's

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

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.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity