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

News

You are here


Visual Scene Analysis


Research

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. 


Teaching

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, or https://caffe2.ai/ and improve certain image reconstruction tasks with semantic information by following some idea of https://arxiv.org/pdf/1701.01698.pdf. 
  • 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!