New Scenes by Decomposition and Reassembly

William Mong Distinguished Lecture by Professor David A. Forsyth
Nov 23, 2017

Date:        November 23, 2017 (Thursday)

Time:       5:00pm – 6:00pm  (Reception: 4:30pm)

Venue:     Lecture Theatre A, Chow Yei Ching Building, HKU

Speaker:  Professor David A. Forsyth

                     Department of Computer Science

                     University of Illinois at Urbana-Champaign


I describe methods that can decompose pictures and reassemble them into pictures of new scenes.  First, I will describe methods to insert computer graphics objects into images of real scenes, while adjusting lighting etc. so as to make it look as if the object "belongs" in the picture.  Second, I will describe methods to cut objects out of one picture and insert them into another.  This process is more complicated, because one must infer a shape representation for the image fragment. Third, I will describe methods that reassemble pictures from a decomposition into useful layers.  Our methods rely on novel conditional image synthesis architectures that can learn to produce multiple, diverse samples of a particular layer consistent with a given input. For example, one might recover the shading of an image, throw that away, then synthesize and apply new shading layers that are consistent with the original albedo, giving the impression the illumination field has changed. Fourth, I will show how our methods can be adapted to edit faces in images, changing makeup, lighting, and some complexion and appearance details. Finally, I will suggest new directions of research in image synthesis network architectures to produce better, more useful, image editing systems.



Professor Forsyth is currently the Fulton-Watson-Copp chair in Computer Science at University of Illinois at Urbana-Champaign, where he moved from U.C Berkeley, where he was also a full professor.  He has occupied the Fulton-Watson-Copp chair in Computer Science at the University of Illinois since 2014. He has published over 170 papers on computer vision, computer graphics and machine learning. He has served as program co-chair for IEEE Computer Vision and Pattern Recognition (CVPR) in 2000, 2011, and 2018, general co-chair for CVPR 2006 and 2015, program co-chair for the European Conference on Computer Vision 2008. He has served six years on the SIGGRAPH program committee. He has received best paper awards at the International Conference on Computer Vision and at the European Conference on Computer Vision. He received an IEEE technical achievement award in 2005 for his research. He became an ACM Fellow in 2014. His textbook, "Computer Vision: A Modern Approach" (joint with J. Ponce and published by Prentice Hall) is now widely adopted as a course text (adoptions include MIT, U. Wisconsin-Madison, UIUC, Georgia Tech and U.C. Berkeley). He served two terms as Editor in Chief, IEEE TPAMI.

Please click here for online registration.

All are welcome!