Google Tech Talk: Urban Reconstruction and Modeling for Building Virtual Worlds

A few weeks ago we featured ran a post on Automatic Architecture: The CityEngine. The post looked into the procedural modelling of cities and more specifcally the work by Pascal Mueller a PhD candidate and research assistant at the Computer Vision Lab of the ETH Zurich, Switzerland.

Peter has teamed up with Peter Wonka from computer science faculty of Arizona State for a Google Tech Talk and at an hour long its worth grabbing a drink and sitting back and watching.

The abstract for the talk is as follows:

Creating digital content for virtual worlds remains a significant challenge, especially for urban environments, which are among the largest and most complex. As display capabilities improve and audience expectations grow, procedural modeling techniques are becoming an increasingly important supplement to traditional modeling software.

In this talk, we present grammar-based, image-based and interactive methods for the efficient creation of urban environments. Thus massive architectural models of high visual quality and geometric detail can be produced at low cost. Selected examples demonstrate solutions to previously unsolved modeling problems, especially to consistent mass modeling with volumetric shapes of arbitrary orientation.

Furthermore,we show massive urban models with unprecedented level of detail, with the virtual rebuilding of the archaeological site of Pompeii as a case in point.

The full talk is embedded below courtesy of YouTube:



Certainly one of the most interesting talks we have seen in quite a while...

Thanks go to Vint Falken for posting the comment that pointed to the tech talk, thanks Vint.