VarCity - semantic and dynamic city modelling

Hayko Riemenschneider
(ETH Zurich, Switzerland)


Virtual city models are used in many game and movie designs, like the industry leading spin-off Procedural (now part of ESRI) for creating stunning 3D urban environments from 2D data. Currently the production of real 3D city models comes at a high cost. Given that the modeling effort needs to be repeated regularly for updating, rendering city model production more efficient is an absolute necessity. Our work creates inverse procedural models, which are built for existing cities.

The modeling is done by analyzing images of real cities and constructing parametrized and semantic models, where we know the number of storeys, shadows cast by new buildings, the position of traffic signs, vegetation, etc. Our research further creates dynamic living 3D city models, which allows for deeper immersion than in current city representations. In particular, four recent papers are presented about efficient semantic segmentation in 3D scenes, superpixel-based surface reconstruction, video summarization and creating city maps about special places in cities.


Hayko Riemenschneider is currently a post-doctoral researcher at the Computer Vision Laboratory at ETH Zurich. He received a Doctor of Philosophy (PhD) in computer science in 2012, a Master of Science (MSc) in 2008 and a Bachelor of Science (BSc) in 2006 from the Graz University of Technology, Austria. Since 2012 he is team and project leader for the ERC project VarCity where the interest lies in large-scale urban modelling. The goal is to reconstruct and augment cities with semantic and dynamic aspects, and have fun while doing so!