Model-Driven 3D Content Creation as Variation

--------------------------------------------------------------------
               ***Joint Seminar***
--------------------------------------------------------------------
The Hong Kong University of Science & Technology

Department of Computer Science and Engineering
Center of Visual Computing and Image Science
--------------------------------------------------------------------
Speaker:	Dr. Hao (Richard) ZHANG
		Simon Fraser University
		Canada

Title:		"Model-Driven 3D Content Creation as Variation"

Date:		Thursday, 21 April 2011

Time:		2:00pm - 3:00pm

Venue:		Room 3412 (via lifts 17/18), HKUST

Abstract:

Content creation in 3D is one of the most fundamental tasks in computer
graphics. The ultimate goal is to allow artists and even novice users to
quickly turn a design concept, such as one from a photograph or sketch,
into a digital 3D model. Creating a 3D model of modest complexity is
typically already a daunting task, thus a sensible strategy is to generate
a novel shape as a variation from one or more existing models. In this
talk, I will present two of our recent works along these lines. First, we
draw creative inspiration from a single photograph and exploit a
pre-analyzed set of 3D candidate models. The user creates a realistic and
readily usable digital 3D model as a photo-guided geometric variation from
one of the 3D candidates. Specifically, the final model is obtained by
deforming a best candidate model so that its silhouette in the appropriate
view matches that of the target object in the photograph. In the second
work, we synthesize new shapes that replicate a certain style extracted
from a set of input shapes. The particular style studied is the
anisotropic scales of the shape parts and the key enabling concept is
style-content separation which facilitates the computation of part
correspondence across the whole set of input shapes exhibiting large style
variations.

******************
Biography:

Hao (Richard) Zhang co-directs the Graphics, Usability, and Visualization
Lab at Simon Fraser University, Canada, where he is an associate professor
in the School of Computing Science. He received his Ph.D. from the Dynamic
Graphics Project (DGP), Department of Computer Science, University of
Toronto in 2003 and M. Math and B. Math degrees from the University of
Waterloo. His research interests include geometry processing, shape
analysis, and computer graphics. He was a winner of the Best Paper Award
from SGP 2008 and the Most Cited Paper Award for the journal
Computer-Aided Design in 2010.