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


You are here

Visual Scene Analysis

Workshop on Imaging and Vision in Siegen!

From March 14th to March 16th, 2018, I am organizing a workshop on Imaging and Vision from Theory to Applications in Siegen. Its goal is to foster the exchange and collaboration between researchers from applied math, imaging, vision and graphics. Please visit the workshop's website to find out more!

Open PhD position

We are looking for a highly motivated PhD candidate with an interest in numerical methods for Computer Vision applications and outstanding mathematical skills. The candidate will work in a DFG project on "Functional Lifting" whose goal it is to extend the applicability of recently developed optimization techniques like sublabel-accurate lifting. This position is a 100% position in the TV-L 13 payscale.


The visual scene analysis group conducts research in the field of mathematical image processing, computer vision, and machine learning with a special focus on the development of energy minimization methods for improving and analysing digital images. In this context we are interested in convex relaxations, functional lifting and multiscale methods as well as the development of efficient convex and nonconvex optimization algorithm for the solution of the corresponding energy minimization problems. Please visit our publications page to find out more about our recent research. 


In the winter semester 17/18 we will of master course on variational methods for computer vision as well as an introdution to numerical methods for visual computing. In the latter you will learn about the basic numerical methods required for solving all kinds of problems in and beyond the area of visual computing, e.g. interpolation, numerical integration, the solution of linear and nonlinear equations, or methods for determining eigenvalues of a matrix. In the course on variational methods you will get some insights into formulating the solution to certain problems as the argument that minimizes a suitable cost function. Such methods are the basis for many state-of-the-art solutions to image processing and computer vision and represent an exciting field of research!

Bachelor or Master Thesis

Feel free to contact me at michael.moeller@uni-siegen.de if you are interested in writing your Bachelor or Master thesis in the field of image processing or computer vision! We have several exciting topics! Please find a list of examples below. I am happy to explain these (sometimes technically sounding) topics in more detail. 

For instance

  • In deep learning, e.g. familiarize yourself with a deep learning framework such as https://www.tensorflow.org, or http://deeplearning.net/software/theano, and improve certain image reconstruction tasks, e.g. working on decompressing images with an architecture motivated by variational decompression methods. 
  • For an applied project, consider the tracking of the common swift in videos taken from a bridge near Biggesee. In particular, tracking the swifts will allow biologists to analyze the forage of the swifts in a level of detail that is currently impossible for such small birds. This project would be carried out in close collaboration with Prof. Klaudia Witte from the in Institute for Biology. 
  • In 3D reconstruction, e.g. familiarize yourself with the relation of images and the camera pose to real world coordinates and try to reimplement an energy minimization approach to surface reconstruction similar to https://www.youtube.com/watch?v=TGg-ujjSsOM (but not in real-time). Extensions of such techniques are able to map large scale geometric features, see e.g. https://www.youtube.com/watch?v=GnuQzP3gty4
  • In optimization, e.g.
    • on joint optimization methods for biconvex or nonconvex problems such as blind deblurring or super resolution. Some suprising results show that there is a gap between good results and faithful optimization (http://www.cvg.unibe.ch/dperrone/tvdb/), which could be investigated in more detail!
    • on optimizing deeply nested functions (as frequently arising in deep learning applications) with proximal splitting methods.
    • on efficient ways to optimize a certain class of constrained convex functions whose proximal operator does not have a closed form.
    • on optimizing nonconvex functions by representing the underlying problem in a higher dimensional space, also known as lifting. See https://arxiv.org/pdf/1512.01383.pdf for an example of a recent work on this topic. I can give clear instructions of how a project on a related topic can look like. 
  • In combining optimization and deep learning methods, e.g. by studying and extending our recent work on using denoising networks as proximal operators, see https://arxiv.org/abs/1704.03488.
  • On multiscale methods for inverse problems, extending the current theory on nonlinear spectral decompositions (see, e.g. https://arxiv.org/pdf/1510.01077.pdf). Such a project could be application driven (https://arxiv.org/pdf/1703.08001.pdf), or based on some mathematical analysis of generalized eigenfunctions, see https://arxiv.org/pdf/1601.02912v1.pdf

If you have ideas for your own research project, let me know!