back to search

Kombinatorische Optimierung in Computer Vision

IN2245Elective Modules8 ECTSEnglishUnregelmäßigDepartment Computer Engineering
AI-edited module sheet. Based on the TUMonline module description, edited for readability.Original in TUMonline

What it is about

You will learn how many problems in computer vision can be formulated as combinatorial optimization problems, in particular via Markov Random Field (MRF) models. You will encounter both polynomially solvable cases and NP-hard tasks and apply methods for exact as well as approximate solutions, e.g. for segmentation, optical flow, stereo and shape matching.

What you will be able to do

  • MRF modeling for multilabel problems
  • Application of pseudo-boolean optimization techniques
  • Knowledge of polynomial algorithms for quadratically submodular problems
  • Understanding and use of approximation methods (e.g. alpha-expansion, belief propagation)
  • Applying the methods to typical vision tasks (segmentation, stereo, optical flow)

What the module consists of

  • LectureConveying the theoretical foundations on MRFs and combinatorial optimization
  • Exercises (Theory & Programming)Deepening and practical application of the methods; programming tasks

Teaching method

  • LectureIntroduction and explanation of theoretical concepts
  • Exercises (Theory & Programming)Application of theory in tasks and implementations
No dates in the current semester
There are no course dates for this module this semester, or they haven't been matched yet.

Module ratings

No ratings for this module yet.

Rate this module

Only fill in the categories you can judge – for each one, either stars and text together or nothing at all.

Lecture
Tutorial
Exam

Reviews are automatically checked before they are published.

Official page in TUMonline · Details are not binding.