Für eine korrekte Darstellung dieser Seite benötigen Sie einen XHTML-standardkonformen Browser, der die Darstellung von CSS-Dateien zulässt.

News

You are here


Computer Vision

Welcome to the Computer Vision Group of the University of Siegen (previously known as the Visual Scene Analysis Group). The group is headed by Prof. Michael Möller. On this website, you can find information about the group members, our courses, publications, final thesis, and open positions.
 

 

 


Research

The Computer Vision Group conducts research in the field of mathematical image processing, computer vision, and machine learning with a special focus on ways to combine machine learning and energy minimization methods. In this context we are interested in provable deep learning as well as optimization techniques such as convex relaxations or functional lifting, and work on (nonlinear) multiscale methods. Please visit our publications page to find out more about our recent research. 
 


News

Our paper "Improving Deep Learning for HAR with shallow LSTMs" won the Best Paper Award at ISWC 2021!

Dr. Yuval Bahat (https://sites.google.com/view/yuval-bahat/home) has joined the University of Siegen via the cofund STAR project in a collaboration with Princeton University (Group of Felix Heide, https://light.princeton.edu/). 
 


Women in Vision Siegen

Two female PhD and one master student at the Computer Vision group started an initiative to encourage more women to study computer science in general and computer vision in particular. They have created a website as a platform and are regularly inviting female researchers to give talks! Please check out https://sites.google.com/view/women-in-vision-siegen and feel free to get in touch - even just for having a coffee, forming a female student and researcher network, or learning more about what life (and research) as a PhD student is like!
 


Bachelor or Master Thesis

To handle the large number of requests for student projects, future Bachelor and Master Theses as well as Studienarbeiten will be supervised by PhD students with feedback to Prof. Möller in larger time periods. The table below shows our current group members, their availability to supervise theses, and the topics/areas they offer theses in. In case you are interested, please contact the respective PhD student directly and include a transcript of your studies. Note that prior knowledge in our fields of research (e.g. gained by attending the chair's lectures) is a requirement to be able to write a final thesis with us. We do not offer internships. If you study computer science and would like to form a project group (Projektgruppe) in the field of machine learning and/or computer vision, please contact Michael Möller at michael.moeller(at)uni-siegen.de.

We offer topics at the end of a short (2-4 weeks) joint program of the Computer Vision and Visual Computing group, where we give an overview of the skills that are necessary for the successful completion of a Studienarbeit/Projektarbeit/Thesis. This program is a good opportunity to self-review and to see if you have the required knowledge and understanding of some basic implementations in computer vision and image processing. Offered topics may or may not be related to the tasks in this program. Students that do not succeed will be recommended courses they can study to learn some basic principles they may be lacking before they re-apply.
The course can be found on Moodle under "Training program for Studienarbeit/Projektarbeit" and also has a Mattermost channel for discussions and further questions.
The kick-off meeting for this semester will be on 14.10.2022 at 15:30 in room H-A 7114, where the tasks will be explained in detail. Please read the AugMix-paper (and necessary papers cited by them) and familiarize yourself with high-performance computing (HPC) clusters (and how to use them) before attending the meeting. A concise list of tasks and deadlines can be found here.

 

PhD Available Slots Topic / Area Email
Hartmut Bauermeister Fully occupied Optimization algorithms and model-informed machine learning hartmut.bauermeister(at)uni-siegen.de
Vaishnavi Gandikota Fully occupied Generative models and deep learning applications in image reconstruction kanchana.gandikota(at)uni-siegen.de
Hannah Dröge Fully occupied Image and video segmentation, hybrid model- and learning-based approaches hannah.droege(at)uni-siegen.de
Marcel Seelbach  2 slots free Optimization methods using quantum computing marcel.seelbach(at)uni-siegen.de
Dr. Zorah Lähner  Fully occupied 3D Shape Analysis and Geometric Deep Learning See topics here

Marius Bock

1 slots free Reducing Human Activity Data Collection through Machine-learned Activity-wise Skips

marius.bock(at)uni-siegen.de