Navigacija

The Space of Human Shapes

Vreme 12. maj 2006. 14:00
Predavač Brian Curless (University of Washington)
Mesto Računski centar

Abstract:

The human form has been the dominant subject of painters and sculptors for millennia. It is the shape we are most attuned to, the one most important to recognize and to build our environments around. Modeling this shape and the way it moves has been a grand challenge in computer science. This task is one of the main components of the graphics Turing test: can a machine fool an observer into thinking the synthetic projection of a moving, talking person is real.

In this talk, I present strides taken in the direction of modeling realistic, time-varying human shape. These strides are formed around the premise that realism depends on samples from reality. The capacity to sample the shape of the real world has grown dramatically in recent years with the advent of fast, reliable imaging sensors and controllable illumination sources. Using existing shape scanners, I will describe how my collaborators and I have developed tools for modeling how a human shape varies over time and how body shape varies across a population. I will also present recent work on modeling the most challenging part of a human: the face. For this task, we have developed a completely new shape scanner that enables us to capture a moving face at high spatio-temporal resolution. To illustrate the success of these shape capture and modeling methods, I will give live demonstrations of interactive human body modeling and three-dimensional video reconstructions of a human face.

Biography:

Brian Curless is an Associate Professor in the Department of Computer Science & Engineering at the University of Washington. He recieved his Ph.D. degree in Electrical Engineering at Satnford University in 1997. He is currently a member of the Graphics and Imaging Laboratory (GRAIL), which is dedicated to innovation in computer graphics and computer vision. His research is focused on 3D photography, human shape simulation and modeling, and digital photography. Brian has published extensively at SIGGRAPH, where he has also twice co-organized a 3D photography course. He has received the Gores Teaching Award (1992), Arthur Samuels Thesis Award (1997), NSF Career Award (1998), Sloan Fellowship (2000), and UW ACM Teaching Award (2004).

P.S. O radu predavaca mozete se informisati i sa njegovog sajta http://www.cs.washington.edu/homes/curless/