ICG/Research/Team Pock/Team

Teresa Klatzer

I have received a MSc in Information and Computer Engineering (Telematics) in 2014 from Graz University of Technology on the topic of "Bi-level Optimization for Support Vector Machines". Since then, I have been working on my PhD studies until autumn 2017 at the Institute for Computer Graphics and Vision in the group of Thomas Pock. My research interests include the development of machine learning and optimization methods for applications in low-level image processing and computational photography. A full CV can be downloaded here. A list of publications can be found here or on my Google Scholar profile.

News

  • 15 Sept 2017: We have been awarded with the Best Paper Award for Variational Networks: Connecting Variational Methods and Deep Learning at GCPR 2017 in Basel, Switzerland!
  • 16 June 2017: Our papers Trainable Regularization for Multi-frame Superresolution and Variational Networks: Connecting Variational Methods and Deep Learning have been accepted to GCPR 2017! These are joint work with Erich Kobler, Daniel Soukup, Kerstin Hammernik and Thomas Pock.
  • 29 May - 2 June 2017: I am looking forward to give a talk at the Applied Inverse Problems (AIP) conference in Hangzhou, China. My talk will be part of the minisymposium on "Non-standard regularisation: theory and applications" organized by Martin Benning and Carola-Bibiane Schönlieb
  • 20 -21 Feb 2017: Invited Talk at a interdisciplinary data science workshop on “Mathematical imaging with partially unknown models” in Cambridge, UK. The topic of this talk was "Learning Variational Networks for Solving Inverse Problems in Imaging".
  • 17-19 Oct 2016: I am looking forward to attend the Google Computer Vision PhD summit in Zürich!
  • 13 May 2016: Oral at the International Conference on Computational Photography (ICCP) 2016 for the paper
  • Joint Demosaicing and Denoising Based on Sequential Energy Minimization. 

    Teresa KlatzerKerstin HammernikPatrick KnöbelreiterThomas Pock
    PDF Slides Code

     

Random

All models are wrong, but some are useful. (George E. P. Box)