AIR Distinguished Speaker Series: Svetlana Lazebnik, Professor, University of Illinois at Urbana-Champaign

Date: April 3, 2024
Time: 11:00am – 12:00pm ET
Location (HYBRID): Center for Computing & Data Sciences, Boston University, Hariri Institute for Computing, 665 Commonwealth Ave, Room 1101 (11th floor), Boston, MA 02215… To access the higher levels, please use the elevators by Saxby’s.

Zoom Details:
https://bostonu.zoom.us/j/94086950630?pwd=QlUrbS8rbHZTUnEvYitmekJTYys0dz09
If the link above does not work, manually enter the Meeting ID and passcode directly into Zoom.
Webinar ID: 940 8695 0630
Passcode: 128281

Speaker: Svetlana Lazebnik, Professor, Department of Computer Science, University of Illinois 

Talk Title: Generative image models for virtual try-on and stylization

Abstract: This talk will survey some of Prof. Lazebnik’s current work, with a focus on generative models for virtual try-on and person image stylization. She will describe two virtual try-on systems, Dressing-in-Order and Street Try-On, one based on generative adversarial networks and the other on diffusion models, aimed at challenging scenarios like multi-garment try-on and in-the-wild try-on. She will also describe systems her group has developed for exemplar-based stylization of images of faces and full-body humans.

Biography: 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, ICCV 2019, and CVPR 2023. She is currently serving as an Editor in Chief of the International Journal of Computer Vision. Her main research themes include scene understanding, joint modeling of images and language, and applications of image generation.

Faculty Host: Bryan Plummer, Assistant Professor, Computer Science, Boston University