Tutorial

Markov Random Fields for Vision and Graphics

Philip Torr
Professor in Computer Vision and Machine Learning
Oxford Brookes University, UK

We are pleased to announce that Professor Philip Torr will give the tutorial on Monday 1st September, on the topic of Markov random fields for vision and graphics. This tutorial will present comprehensive coverage of the theory of Markov random fields, optimization algorithms, and applications in vision and graphics. Topics will include:

  • Introduction to Markov random fields
  • Dynamic programming, graph cuts, dynamic graph cuts & multi-way graph cuts
  • Relation to belief propagation & level set methods
  • Higher order energies
  • Object extraction, segmentation & alpha matting
  • Object matching, registration, recognition & pose estimation
  • Stereo, optic flow & multi-view stereo
  • Texture & video texture synthesis

Philip Torr is Professor in Computer Vision and Machine Learning at Oxford Brookes University. He did his PhD (DPhil) at the Robotics Research Group of the University of Oxford under Professor David Murray of the Active Vision Group. He worked for another three years at Oxford as a research fellow, and still maintains close contact as visiting fellow there. He left Oxford to work for six years as a research scientist for Microsoft Research, first in Redmond USA in the Vision Technology Group, then in Cambridge UK founding the vision side of the Machine learning and perception group. He is now a Professor in in Computer Vision and Machine Learning at Oxford Brookes University, where he has brought in over one million pounds in grants for which he is PI. Philip Torr has won several awards, including the Marr prize (the highest honour in vision) in 1998. Recently he, together with members of his group, has won several other awards including most recently an honorary mention at the NIPS 2007 conference for the paper P. Kumar, V. Kolmorgorov, and P.H.S. Torr, An Analysis of Convex Relaxations for MAP Estimation, In NIPS 21, Neural Information Processing Conference, 2007. Recent SIGGRAPH work on VideoTrace with the University of Adelaide has been featured extensively on the internet including slashdot. He was involved in the algorithm design for Boujou (for which he receives royalties, along with Paul Beardsley, Andrew Fitzgibbon and Andrew Zisserman) released by 2D3. Boujou has won a clutch of industry awards, including Computer Graphics World Innovation Award, IABM Peter Wayne Award, and CATS Award for Innovation, and an EMMY. He continues to work closely with this Oxford based company as well as other companies such as Sony and Sharp.