Teaching

Winter Semester 24/25

Master Practical: Image & Video Synthesis

Course Info: https://moodle.lmu.de/course/view.php?id=35376, LSF 16549, 6 SWS
Lecturer: Prof. Björn Ommer
Date: By arrangement (Nach Vereinbarung)
Location: Akademiestr. 7, 1st floor
Recommended prerequisites for participants:
– Strong programming skills
– Prior practical experience in machine learning, typically acquired through one of the standard ML courses

Course Description

Modern Deep Learning has fundamentally changed Artificial Intelligence. Novel applications as well as significant improvements to old problems continue to appear at a staggering rate. Especially the areas of image and video understanding, retrieval, and synthesis have seen tremendous improvements and even the human baseline has been outperformed in several difficult applications.

The algorithms and the fundamental research in deep Machine Learning and Computer Vision that are driving this revolution are improving at an ever-increasing rate. The goal of this practical lab is, therefore, to give students hands-on experience with the state-of-the-art in this field of research. We will work on current problems in Computer Vision and Machine Learning and build on current algorithms to practically implement novel solutions. Consequently, the practical is also a good opportunity to take a close look at this area of research and prepare for a potential future final thesis.

Topics include but are not limited to:

  • Image & video synthesis
  • Visual superresolution and Image completion
  • Artistic style transfer
  • Interpretability of deep models
  • Modern deep learning approaches, such as transformers and self-attention, invertible neural networks, diffusion models, etc.

Notes: Central Registration via Moodle

Master Practical: Visual Representation Learning

Course Info: https://moodle.lmu.de/course/view.php?id=35375, LSF 16548, 6 SWS
Lecturer: Prof. Björn Ommer
Date: By arrangement (Nach Vereinbarung)
Location: Akademiestr. 7, 1st floor
Recommended prerequisites for participants:
– Strong programming skills
– Prior practical experience in machine learning, typically acquired through one of the standard ML courses

Notes: Central Registration via Moodle

Seminar: Creating Art(efacts): Computer-based Image Generation and Editing

Course Info:
Master Seminar for Art students
Bachelor Seminar for Computer Science students
Moodle: https://moodle.lmu.de/course/view.php?id=35357
LSF 09428
3 SWS

Lecturer: Prof. Björn Ommer
Date: Tuesdays, 10 am – 1 pm, 15.10.2024 until 04.02.2025
Location: Akademiestr. 7, 1st floor, room 105

Course Description

Over the past two years, there has been a surge in new AI-based image generation and editing tools that do not require special computer skills, but are usable by laypersons, artists, and designers. This has been largely influenced by the publicly available, open-source “Stable Diffusion” model (https://ommer-lab.com/stable-diffusion). Now many researchers, start-ups, and artists are investigating downstream tasks without the need for a high-performance GPU cluster to train a base model. Moreover, a number of closed-source services such as Midjourney and Open AI’s Dall-E 2 have also drawn a lot of attention.

The foundation of this technology is the task of generating a single image solely based on a textual description of what should be depicted in the image. Examples of this can be found on websites such as https://lexica.art/. This technology can be extended to include additional information, such as depth maps, and allows for flexible image editing by changing existing objects based on text or removing parts of the image and filling it while paying attention to the remaining image. The latest advances also allow for generation or modification of video as well as rendering 3D scenes.

These topics and more will be covered in our seminar, where we will investigate AI-based image and video editing and generation techniques. Each student will focus on a specific topic. The objective of this seminar is then to investigate the connection between these techniques and the students’ respective fields of study and the greater societal and research implications. We will explore potential applications and issues in applying this technology. Each student will give a presentation of their ideas and write a report about the technique and its potential applications and implications.

Notes:
Central Restistration via LSF for Art students.
Central Registration via Moodle for Computer Science students.

Bachelor Software Development Practical: Computer Vision & Deep Learning

Course Info: https://moodle.lmu.de/enrol/index.php?id=35360, LSF 16456, 11 SWS
Lecturer: Prof. Björn Ommer, Ming Gui
Date: Thursdays, 10:00 – 12:00, 17.10.2024 until 06.02.2025
Location: Akademiestr. 7, 1st floor, room 105

Course Description

Machine learning is changing the world. It can be found in almost all segments including healthcare services, education, transport, food, entertainment and many more. Specifically, in the field of computer vision, machine learning techniques have enabled programs to interpret and understand the world, sometimes even better than humans.

In this course, we will work on several projects to solve several computer vision tasks using python. The students will have a chance to get their hands on the classical (or potentially deep) machine learning algorithms in teams, and apply those techniques to some of the most interesting topics in computer vision.

Notes: Central Registration via Moodle

Oberseminar: High-Level Vision

Lecturer: Prof. Björn Ommer
Date: Fridays, 12:00 -13:45
Location: Akademiestr. 7, 1st floor, Room 105

Notes: Registration closed

Summer Semester 2024

Lecture and Exercises: Generative AI and Visual Synthesis

Course Info: https://moodle.lmu.de/enrol/index.php?id=32420
Lecturer: Prof. Björn Ommer, Ming Gui
Lecture Date/Location: Thursdays, 12:15 – 13:45 / Geschwister-Scholl-Platz 1, room E 004
Exercises Date/Location: Fridays, 10:15 – 11:45/ Geschwister-Scholl-Platz 1, room E 004
Supervisor: Ming Gui

Course Description

This lecture focuses on deep learning approaches in computer vision with a particular emphasis on generative approaches that not only analyze, but in particular synthesize novel images and video.

Modern deep learning has fundamentally changed artificial intelligence. Computer vision was at the forefront of many of these developments and has tremendously benefited over the last decade from this progress. Novel applications as well as significant improvements to old problems continue to appear at a staggering rate. Especially the areas of image and video synthesis and understanding have seen previously unthinkable improvements – and provided astounding visual results with wide-ranging implications (trustworthiness of AI, deep fakes).

We will discuss how a computer can learn to understand images and videos based on deep neural networks. The lecture will briefly review the necessary foundations of deep learning and computer vision and then cover the latest works from this quickly developing field. The practical exercises that accompany this course will provide hands-on experience and allow attendees to practice while building and experimenting with powerful image generation architectures.

Topics include but are not limited to:

  • Image & video synthesis
  • Visual superresolution and Image completion
  • Artistic style transfer
  • Interpretability, trustworthyness of deep models
  • Self-supervised learning
  • Modern deep learning approaches, such as transformers and self-attention, invertible neural networks, diffusion models, etc.

Notes: Self registration via Moodle, questions re. registration: assist.mvl@lrz.uni-muenchen.de

Master Practical: Image & Video Synthesis

Course Info: https://moodle.lmu.de/enrol/index.php?id=32421
Lecturer: Prof. Björn Ommer
Date: By arrangement (Nach Vereinbarung)
Location: Akademiestr. 7, 1st floor

Course Description

Modern Deep Learning has fundamentally changed Artificial Intelligence. Novel applications as well as significant improvements to old problems continue to appear at a staggering rate. Especially the areas of image and video understanding, retrieval, and synthesis have seen tremendous improvements and even the human baseline has been outperformed in several difficult applications.

The algorithms and the fundamental research in deep Machine Learning and Computer Vision that are driving this revolution are improving at an ever-increasing rate. The goal of this practical lab is, therefore, to give students hands-on experience with the state-of-the-art in this field of research. We will work on current problems in Computer Vision and Machine Learning and build on current algorithms to practically implement novel solutions. Consequently, the practical is also a good opportunity to take a close look at this area of research and prepare for a potential future final thesis.

Topics include but are not limited to:

  • Image & video synthesis
  • Visual superresolution and Image completion
  • Artistic style transfer
  • Interpretability of deep models
  • Modern deep learning approaches, such as transformers and self-attention, invertible neural networks, diffusion models, etc.

Notes: Central Registration via Moodle.

Master Practical: Visual Representation Learning

Course Info: https://moodle.lmu.de/enrol/index.php?id=32422
Lecturer: Prof. Björn Ommer
Date: By arrangement (Nach Vereinbarung)
Location: Akademiestr. 7, 1st floor

Notes: Central Registration via Moodle.

Seminar: Creating Art(efacts): Computer-based Image Generation and Editing

Course Info:
Master Seminar for Art students
Bachelor Seminar for Computer Science students
Moodle:
https://moodle.lmu.de/course/view.php?id=32802
https://moodle.lmu.de/course/index.php?categoryid=3308
LSF 09533

Lecturer: Prof. Björn Ommer
Date: Tuesdays, 10am
Location: Akademiestr. 7, 1st floor, room 105

Course Description

Over the past two years, there has been a surge in new AI-based image generation and editing tools that do not require special computer skills, but are usable by laypersons, artists, and designers. This has been largely influenced by the publicly available, open-source “Stable Diffusion” model (https://ommer-lab.com/stable-diffusion). Now many researchers, start-ups, and artists are investigating downstream tasks without the need for a high-performance GPU cluster to train a base model. Moreover, a number of closed-source services such as Midjourney and Open AI’s Dall-E 2 have also drawn a lot of attention.

The foundation of this technology is the task of generating a single image solely based on a textual description of what should be depicted in the image. Examples of this can be found on websites such as https://lexica.art/. This technology can be extended to include additional information, such as depth maps, and allows for flexible image editing by changing existing objects based on text or removing parts of the image and filling it while paying attention to the remaining image. The latest advances also allow for generation or modification of video as well as rendering 3D scenes.

These topics and more will be covered in our seminar, where we will investigate AI-based image and video editing and generation techniques. Each student will focus on a specific topic. The objective of this seminar is then to investigate the connection between these techniques and the students’ respective fields of study and the greater societal and research implications. We will explore potential applications and issues in applying this technology. Each student will give a presentation of their ideas and write a report about the technique and its potential applications and implications.

Notes:
Central Restistration via LSF for Art students.
Central Registration via Moodle for Computer Science students.

Oberseminar: High-Level Vision

Lecturer: Prof. Björn Ommer
Date: Fridays, 12:00 -13:45
Location: Akademiestr. 7, 1st floor, Room 105

Notes: Registration closed

Winter Semester 23/24

Master Seminar: Creating Art(efacts): Computer-based Image Generation and Editing

Course Info: Interdisciplinary Seminar. https://moodle.lmu.de/course/view.php?id=29464
Lecturer: Prof. Björn Ommer
Date: Tuesdays, 10:00
Location: Akademiestr. 7, 1st floor, room 105

Notes: Registration Closed.

Master Practical: Image & Video Synthesis

Course Info: https://moodle.lmu.de/enrol/index.php?id=29214
Lecturer: Prof. Björn Ommer
Date: TBD
Location: TBD

Notes: Registration Closed.

Master Practical: Visual Representation Learning

Course Info: https://moodle.lmu.de/enrol/index.php?id=29213
Lecturer: Prof. Björn Ommer
Date: TBD
Location: TBD

Notes: Registration Closed.

Oberseminar: High-Level Vision

Lecturer: Prof. Björn Ommer
Date: Mondays, 10:00 – 12:00
Location: Akademiestr. 7, 1st floor, Room 105

Notes: Registration closed

Bachelor Software Development Practical: Computer Vision & Deep Learning

Course Info: https://moodle.lmu.de/enrol/index.php?id=29211
Lecturer: Prof. Björn Ommer, Ming Gui
Date: Thursdays, 10:00 – 12:00
Location: Akademiestr. 7, 1st floor, Room 105

Notes: Registration Closed.

Summer Semester 2023

Lecture and Practical: Computer Vision and Deep Learning: Automatic Image Understanding & Recognition

Lecturer: Prof. Björn Ommer
Lecture Date/Location: Wednesdays, 10:00 – 12:00 / Theresienstr. 39, B 139
Excercises Date/Location: Fridays, 10:00 – 12:00 / Main Building, M 114

Notes: Self-enrollment on Moodle until April 6, 2023: https://moodle.lmu.de/course/view.php?id=26244.

Master Seminar: Creating Art(efacts): Computer-based Image Generation and Editing

Course Info: Interdisciplinary Seminar
Lecturer: Prof. Björn Ommer
Date: Tuesdays, 10:00
Location: Akademiestr. 7, 1st floor, room 105

Notes: Registration required via Moodle https://moodle.lmu.de/course/view.php?id=26582

Master Practical: Machine Vision and Learning

Course Info: https://uni2work.ifi.lmu.de/course/S23/IfI/MVL-MPrac
Lecturer: Prof. Björn Ommer
Date: By arrangement (Nach Vereinbarung)
Location: Akademiestr. 7, 1st floor

Notes: Central registration via Uni2Work (see link above)

Oberseminar: High-Level Vision

Lecturer: Prof. Björn Ommer
Date: Mondays, 10:00 – 12:00
Location: Akademiestr. 7, 1st floor, Room 105

Notes: Registration closed

Practical: Software Development Computer Vision & Deep Learning

Course Info: https://uni2work.ifi.lmu.de/course/S23/IfI/CompVisDLSoft
Lecturer: Prof. Björn Ommer, Ming Gui
Date: Thursdays, 10:00 – 12:00
Location: Akademiestr. 7, 1st floor

Notes: Central Registration via Uni2work (see link above)

Winter Semester 22/23

Machine Learning & (Automatic) Image Understanding – Seminar

Course Info: Course Website
Lecturer: Björn Ommer
Starting: 18.10.2022
Date: Tuesdays, 10:15
Location: Akademiestr. 7, Room 105

Notes: Registration required before 07.10.2022

Machine Vision and Learning – Master Seminar

Course Info: This seminar on the CS department course website
Lecturer: Björn Ommer
Starting: 20.10.2022
Date: Thursdays, 10:15 – 11:45
Location: Akademiestr. 7, Room 105

Notes: Registration required via uni2work, please check back soon for link.

Machine Vision and Learning – Master Practical

Course Info: This practical on the CS department course website
Lecturer: Björn Ommer
Date: tba
Location: Akademiestr. 7, Room 105

Notes: Registration required via uni2work, please check back soon for link.

High-Level Computer Vision – Oberseminar

Lecturer: Björn Ommer
Date: tba
Location: Akademiestr. 7, Room 105

Notes: Registration closed

Summer Semester 2022

Lecture: Computer Vision and Deep Learning: Visual Synthesis

Lecturer: Björn Ommer
Starting: 27.04.2022
Lecture Date/Location: Wednesdays, 14:15 – 15:45 / Geschw.-Scholl-Pl. 1 (B), B 106
Excercises Date/Location: Fridays, 10:15 – 11:45 / Schellingstr. 3 (S), S 005

Notes: Registration required before 20.04.2022.

Machine Vision and Learning – Master Practical

Lecturer: Björn Ommer
Date: tba
Location: Akademiestr. 7

Notes: Registration required due to limited number of participants

High-Level Computer Vision – Oberseminar

Lecturer: Björn Ommer
Date: tba
Location: Akademiestr. 7, Room 105

Notes: Registration closed

Winter Semester 21/22

Machine Vision and Learning – Master Practical

Course Info: This practical on the CS department course website
Lecturer: Björn Ommer
Date: tba
Location: Akademiestr. 7

Notes: Registration required due to limited number of participants

Machine Vision and Learning – Master Seminar

Course Info: This seminar on the CS department course website
Lecturer: Björn Ommer
Date: Thursdays, 12:15 – 13:45
Location: Akademiestr. 7, Room 105

Notes: Registration required due to limited number of participants

High-Level Computer Vision – Oberseminar

Lecturer: Björn Ommer
Date: tba
Location: Akademiestr. 7, Room 105

Notes: Registration closed