Tuesday, May 6, 2003
B17 Upson Hall
University of North Carolina, Chapel Hill
Host: Kavita Bala
Data-Driven Modeling in Computer Graphics
The field of computer graphics abounds with modeling and simulation problems. Among these are the representation of surface shape, the description of surface reflectance, the probabilistic modeling of small-scale variations, and the application of physics for simulating the dynamics of rigid and elastic materials. During its formative years, computer graphics has focused largely on developing algorithms and systems for performing efficient simulations that transform these analytic representations into images and animations. At present, the simulation framework for computer graphics is very mature. In last ten years, we have also witnessed significant technological developments in the areas of high-quality sensors and measurement devices. However, the data provided from these devices are frequently incompatible with the representations assumed by most computer graphics systems.
In this talk I will explore new approaches to computer graphics that attempt to bridge the dichotomy between parametric and empirical modeling. These approaches differ from the classical “simulation-based” computational model that pervades today’s computer graphics, and instead depends more on the tools of interpolation and signal processing for synthesis. I will discuss three specific computer graphics applications of data-driven modeling in this talk. The first, called image-based rendering, addresses the problem of rendering novel views directly from a collection of photographs without reconstructing intermediate three-dimensional models. In a second application, I will discuss the problem of interpolating and extrapolating new reflectance models (specifically isotropic BRDFs) from a collection of acquired samples. Finally, I will discuss a new approach to human-figure modeling, which incorporates millions of observations to construct a data-driven deformable model of a specific actor. This model can, in turn, be reanimated with original motions.
Leonard McMillan is an Associate Professor of Computer Science at the University of North Carolina in Chapel Hill. Leonard received his Bachelors (’83) and Masters (’84) degrees in Electrical Engineering from Georgia Institute of Technology. Leonard received his Ph.D. in Computer Science from the University of North Carolina at Chapel Hill (’97). Leonard has been a Member of Technical Staff at AT&T Bell Laboratories where he worked in the Digital Signal Processing Architecture Group and was a co-architect of the AT&T Pixel Machine. Leonard has also worked as a Senior Staff Engineer at Sun Microsystems where he helped develop several visualization and multimedia products.
Leonard is a pioneer in the field of image-based rendering. Image-based rendering is a new approach to computer graphics where scenes are rendered directly from a collection of reference images rather than a geometric model. Leonard is also interested in a wide range of related topics including computer graphics rendering, imaging methods and technologies, three-dimensional display technologies, computer graphics hardware, and the fusion of image processing, multimedia, and computer graphics.