[Theory] [TTIC Talks] 9/30 Research at TTIC: Svetlana Lazebnik, University of Illinois at Urbana-Champaign

[Brandie Jones]

*When:*        Friday, September 30th at *12:30pm CT   *

*Where:*       Talk will be given live, *in-person* at
                       TTIC, 6045 S. Kenwood Avenue
                       5th Floor, Room 530

*Virtually: *     via *Panopto *(*Join Here
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=fa22380f-e3bc-4238-b2f8-af1800ec9cfb>*
)

*Who: *            Svetlana Lazebnik, University of Illinois at
Urbana-Champaign


*Title:*             Playing with GANs for Virtual Try-On and Face
Stylization

*Abstract:     * I will open the talk by sharing some thoughts on the
current state of computer vision research, particularly on the challenges
facing academics at this unprecedented time. Against this background, I
will survey some of my group’s current work, with a focus on generative
models for outfit and face editing and stylization. I will describe a
virtual try-on system called Dressing in Order (DiOr), which supports 2D
pose transfer, virtual try-on, and several fashion editing tasks. The key
to DiOr is a recurrent generation pipeline to sequentially put garments on
a person, so that trying on the same garments in different orders will
result in different looks. Then I will talk about MultiStyleGAN, a simple
yet effective face stylization method that is capable of producing multiple
different stylizations at once by fine-tuning a single pre-trained
StyleGAN2 generator using a single example for each target style. This
method can learn up to a dozen stylizations at once, which brings
considerable efficiency gains over separate fine-tuning, and actually
improves the quality of stylizations by mitigating overfitting.

*Bio:  *    Svetlana Lazebnik received a Ph.D. in Computer Science at the
University of Illinois in 2006. After serving as an assistant professor at
the University of North Carolina at Chapel Hill from 2007 to 2011, she
returned as faculty to the University of Illinois, where she is currently a
Full Professor in the Department of Computer Science. Her notable awards
include the NSF CAREER Award (2008), Microsoft Research Faculty Fellow
(2009), Sloan Research Fellow (2013), and IEEE Fellow (2021). Her CVPR 2006
paper on Spatial Pyramid Matching received the 2016 Longuet-Higgins Prize
for a paper with a significant impact on computer vision. She served as
Program Chair for ECCV 2012 and ICCV 2019, and is currently serving as
Program Chair for CVPR 2023 and Editor in Chief of the International
Journal of Computer Vision. Her main research themes include scene
understanding, joint modeling of images and language, and deep learning
techniques for visual recognition problems.



*********************************************************************************************

*Presence at TTIC requires being fully vaccinated for COVID-19 or having a
TTIC or UChicago-approved exemption. Masks are required in all common
areas. Full visitor guidance is available at ttic.edu/visitors
<http://ttic.edu/visitors>.*

*********************************************************************************************

*Research at TTIC Seminar Series*

TTIC is hosting a weekly seminar series presenting the research currently
underway at the Institute. Every week a different TTIC faculty member will
present their research.  The lectures are intended for students seeking
research topics and advisors and for the general TTIC and University of
Chicago communities interested in hearing what their colleagues are up to.


-- 
*Brandie Jones *
*Administrative Assistant*
Toyota Technological Institute
6045 S. Kenwood Avenue
Chicago, IL  60637
www.ttic.edu

Working Remote on Tuesdays
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20220923/af962e6a/attachment-0001.html>