There is a sign-up schedule for this event that can be found at

http://apps.cs.utexas.edu/talkschedules/cgi/list_events.cgi

Type o

f Talk: UTCS Faculty Candidate

Speaker/Affiliation: Evangelos Kalogera

kis/Stanford University

Talk Audience: UTCS Faculty, Graduate Student

s, Undergraduate Students and Outside Interested Parties

Date/Time: T

hursday, April 26, 2012, 11:00 am

Location: ACES 2.302

Host: D

on Fussell

Talk Title: Data-driven shape analysis and synthesis

T

alk Abstract:
The emergence of modern geometry acquisition devices, such
as the Kinect, and the appearance of large-scale shape repositories, suc

h as the Google Warehouse, are revolutionizing computer graphics, making

three-dimensional content ubiquitous. The need for algorithms that understa

nd and intelligently process 3D shapes is thus greater than ever.

In t

his talk, I will describe a new generation of algorithms that analyze and

synthesize complex three-dimensional shapes. The algorithms are based on pr

obabilistic models that reason about both geometry and semantics. In contra

st to traditional approaches that consider individual shapes in isolation a

nd require laborious hand-tuning, these algorithms learn from collections

of shapes. Specifically, I will present a data-driven shape segmentation t

echnique that outperforms all previous approaches to shape segmentation. I

will then describe a shape synthesis technique that can construct high-qual

ity novel shapes from complex domains, such as aircraft, ships, and furn

iture. Finally, I will discuss new opportunities for geometry processing a

nd 3D modeling enabled by these algorithms.

Bio:
Evangelos Kalogerak

is is a postdoctoral researcher in computer science at Stanford university.
His research deals with the development of computer graphics techniques th

at support human creativity and automate complex visual content processing

tasks for novice users, scientists and artists. He is particularly interes

ted in developing machine learning algorithms for 3D content analysis and s

ynthesis. He earned a PhD from the department of Computer Science at the Un

iversity of Toronto. He has been awarded with the NSERC Alexander Graham Be

ll research fellowship.