Timo Milbich

PhD student in Computer Vision and Deep learning supervised by Prof. Björn Ommer


Heidelberg University
Mathematikon (A), INF 205
Room 04.324
D-69120 Heidelberg
Tel. +49 6221 / 14808

Email: timo.milbich (at) iwr.uni-heidelberg (dot) de

Curriculum Vitae

  • since 2014: PhD student (Heidelberg University)
  • 2014: MSc. Scientific Computing (Heidelberg University)
  • 2012: BSc. Mathematics (University of Applied Science Stuttgart)

Scientific Interests

  • Deep Learning
  • Video Analysis
  • Activity Understanding
  • Unsupervised Learning
  • Representation Learning
  • Generative Models


Lorenz, D, Bereska, L, Milbich, T and Ommer, B (2019). Unsupervised Part-Based Disentangling of Object Shape and Appearance
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (oral)
[Project Site] [Pdf] [Bibtex]

Esser, P*, Haux, J*, Milbich, T* and Ommer, B (2018). Towards Learning a Realistic Rendering of Human Behavior
Proceedings of the IEEE European Conference on Computer Vision (ECCV) Workshops
[Project Site] [Pdf] [Bibtex]

Milbich, T, Bautista, M, Sutter, E and Ommer, B (2017). Unsupervised Video Understanding by Reconciliation of Posture Similarities
Proceedings of the IEEE International Conference on Computer Vision (ICCV)
[Project Site] [Pdf] [Bibtex]

Antic, B, Milbich, T, and Ommer, B (2013). Less is more: Video Trimming for Action Recognition
Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops

Muffert, M, Milbich, T, Pfeiffer, D and Franke, U (2012). May I enter the roundabout? A time-to-contact computation based on stereo-vision
IEEE Intelligent Vehicles Symposium (IV) (Best Paper Award)

* indicates equal contribution