Lecture: Markov Random Fields for Vision and Graphics


  • Lecturer(s):
  • Start: 19.04.2016
  • Dates: Tues. 10:30 (s.t.) - 12:00, LBH / VR Lab I.80
  • Course number: MA-INF 2117
  • Curriculum: Master
  • Effort: 6 CP
  • Exams: 26.07.2016, 10:30-12:00 at LBH I.42



This course addresses advanced topics for Markov Random Fields and their use in applications for vision and graphics.  We will cover advanced topics in inference and learning such as loopy belief propagation, MCMC sampling, graph cuts and move-making algorithms, dual decomposition and structured learning.  Applications discussed will include low and mid-level vision and graphics concepts such as optical flow and stereo depth, super-resolution, superpixels, texture synthesis, segmentation as well as higher-level concepts such as semantic segmentation and object detection.

It is recommended but not required to have taken Probabilistic Graphical Models (MA-INF 4315) as a pre-requisite for this course.  Those who have not taken Probabilistic Graphical Models should be comfortable with concepts in probability theory and optimization.


Due to Pentecost week, there will be no lecture on May 17; the exercise on May 19 for presenting solutions to the coding assignment is shifted to June 2.


Additional Documents

Assignment Sheets

Exercise 1: Exercise01
Assignment sheet  (PDF document, 115 KB)
Exercise 2: Exercise02
Assignment sheet  (PDF document, 178 KB)
Exercise 3: Exercise03
Assignment sheet  (PDF document, 170 KB)
Exercise 4: Exercise04
Assignment sheet  (PDF document, 158 KB)