Lecture: Markov Random Fields for Vision and Graphics
Course
- Lecturer(s):
- Start: 19.04.2017
- Dates: Wed. 10:30 (s.t.) - 12:00, LBH / VR Lab I.80
- Course number: MA-INF 2117
- Curriculum: Master
- Effort: 6 CP
- Exams: 03.08.2017, 14:00 - 16:00, LBH / Hörsaal III.03 (second exam: 19.09.2017, 14:00 - 16:00, LBH / Hörsaal III.03)
Exercises
- Tutor(s):
- Start: tbd
- Dates: Wed. 14:00 (s.t.) - 15:30, LBH / VR Lab I.80
Description
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.
Slides
- 01 Introduction (PDF document, 9.9 MB)
- 02 MRFs and BeliefProp (PDF document, 2.2 MB)
- 03 Superresolution and TextureSynthesis (PDF document, 18.0 MB)
- 04 GraphCuts (PDF document, 7.3 MB)
- 05 ForegroundSeg (PDF document, 12.6 MB)
- 06 Movemaking (PDF document, 1.6 MB)
- 07 OpticFlowDepth (PDF document, 3.7 MB)
- 08 CRF (PDF document, 1.6 MB)
- 08 CRF corrected (PDF document, 1.6 MB)
- 09 Segmentation (PDF document, 21 MB)
- 10 DualDecomp (PDF document, 2.9 MB)
- 11 ObjectDetection (PDF document, 71 KB)
Additional Documents
- 01 KollerReadings (PDF document, 1.1 MB)
- 02 HigherOrderModels (PDF document, 2.8 MB)
- 03 StereoIntro (PDF document, 9.6 MB)
- 04 OpticFlowIntro (PDF document, 1.1 MB)
- 05 PartBasedModel (PDF document, 18.7 MB)
Assignment Sheets
|
Exercise 1: Exercise01 Assignment sheet (PDF document, 127 KB) |
|
Exercise 2: Exercise02 Assignment sheet (PDF document, 176 KB)
|
|
Exercise 3: Exercise03 Assignment sheet (PDF document, 173 KB)
|
|
Exercise 4: Exercise04 Assignment sheet (PDF document, 266 KB)
|