Maren Awiszus, M.Sc.
Leibniz Universität Hannover
Institut für Informationsverarbeitung
Appelstr. 9A
30167 Hannover
phone: +49 511 762-5017
fax: +49 511 762-5333
office location: room 1302

Maren Awiszus studied Electrical Engineering at Leibniz Universität Hannover. In May 2017, she finshed her Master's Degree with her thesis on "Alignment of 3D-Sequences of Facial Expressions" at the Institut für Informationsverarbeitung (TNT). Starting June 2017, she started a job as a research assistant and is working towards her PhD degree at the same Intitute.

Starting 2018, Maren Awiszus' PhD is financially aided by the Caroline Herschel Program.


Research Interests

  • Machine Learning with Neural Networks
    • Content Generation
      • Generative Adversarial Networks
      • Images
      • Video Game Levels
    • Subspace Analysis
      • Autoencoders
      • Disentanglement
  • Synthetic Training Data
Show selected publications only
  • Maren Awiszus, Frederik Schubert, Bodo Rosenhahn
    Wor(l)d-GAN: Towards Natural Language Based PCG in Minecraft
    IEEE Transactions on Games, IEEE, February 2022, edited by Georgios Yannakakis
  • Maren Awiszus, Frederik Schubert, Bodo Rosenhahn
    World-GAN: a Generative Model for Minecraft Worlds
    IEEE Conference on Games, August 2021
  • Frederik Schubert, Maren Awiszus, Bodo Rosenhahn
    TOAD-GAN: a Flexible Framework for Few-Shot Level Generation in Token-Based Games
    IEEE Transactions on Games, IEEE, March 2021, edited by Julian Togelius
  • Maren Awiszus, Frederik Schubert, Bodo Rosenhahn
    TOAD-GAN: Coherent Style Level Generation from a Single Example
    AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment Best Student Paper Award , October 2020
  • Maren Awiszus, Hanno Ackermann, Bodo Rosenhahn
    Learning Disentangled Representations via Independent Subspaces
    Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW), October 2019
  • Maren Awiszus, Stella Graßhof, Felix Kuhnke, Jörn Ostermann
    Unsupervised Features for Facial Expression Intensity Estimation over Time
    Computer Vision and Pattern Recognition Workshops (CVPRW), June 2018
  • Maren Awiszus, Bodo Rosenhahn
    Markov Chain Neural Networks
    Computer Vision and Pattern Recognition Workshops (CVPRW), June 2018
  • Hendrik Hachmann, Maren Awiszus, Bodo Rosenhahn
    3D braid guide hair reconstruction using electroluminescent wires
    The Visual Computer, Springer, Vol. 34, No. 6, pp. 793-804, June 2018, edited by Nadia Magnenat-Thalmann
Other activities

Additionally, Maren Awiszus is a supervisor for the Video Game AI Competition Team.