News Archives

[Colloquium] Computer Graphics 2.0 The Virtual World is not Enough

September 11, 2009

Watch Colloquium: 

Quicktime file(363 MB)
AVI file (458 MB)

  • Date: Friday, Sep 11th, 2009 
  • Time: 12 am — 12:50 pm 
  • Place: Centennial Engineering Center, Room 1041

Prof. Dr.-Ing. Marcus Magnor 
Computer Graphics Lab TU Braunschweig

Abstract: Expectations on computer graphics performance are rising continuously: whether in flight simulators, surgical planning systems, or computer games, ever more realistic rendering results are to be achieved at real-time frame rates. In fact, thanks to progress in graphics hardware as well as rendering algorithms, visual realism is today within reach of off-the-shelf PCs. With rapidly advancing rendering capabilities, the modeling process is becoming the limiting factor in computer graphics. Higher visual realism can be attained only by having available more detailed and accurate scene descriptions. So far, however, modeling 3D geometry and object texture, surface reflectance characteristics and scene illumination, character animation and emotion is a labor-intensive, tedious process. The cost of visually authentic content creation using conventional approaches increasingly threatens to stall further progress in realistic rendering applications.

In my talk, I will present an alternative modeling approach. I will discuss and exemplify different approaches on how to recover digital models from real-world imagery. The models may be derived either based on the physics of the scene, or by regarding perceptional consequences only. While the former approach yields physically meaningful information about the scene, approaches of the latter kind may allow for easier modeling and more natural-appearing rendering results. This opens up various new opportunities, extending the scope of computer graphics beyond virtual worlds to encompass visual reality.

Bio: Marcus Magnor heads the Computer Graphics Lab of the Computer Science Department at Braunschweig University of Technology (TU Braunschweig). He received his BA (1995) and MS (1997) in Physics from the University of Würzburg and the University of New Mexico, respectively, and his PhD (2000) in Electrical Engineering from the Telecommunications Lab at the University of Erlangen. For his post-graduate studies, he joined the Computer Graphics Lab at Stanford University. In 2002, he established the Independent Research Group Graphics-Optics-Vision at the Max-Planck-Institut Informatik in Saarbrücken. He completed his habilitation and received the venia legendi in Computer Science from Saarland University in 2005. His research interests meander along the visual information processing pipeline, from image formation, acquisition, and analysis to image synthesis, display, perception, and cognition. Recent and ongoing research topics include video-based rendering, 3D-TV, augmented vision, video editing, optical phenomena, as well as astrophysical visualization (research).