Abstract:
Intrinsic images are maps of surface properties, such as depth, normal and albedo. In this talk, Prof Forsyth will demonstrate and review the results of simple experiments suggesting that very good modern depth, normal and albedo predictors are strongly sensitive to lighting – if one relight a scene in a reasonable way, the reported depth will change.

Biography:
David is currently the Fulton-Watson-Copp Chair in Computer Science at University of Illinois at Urbana-Champaign, where he moved from U.C Berkeley, also as a full professor. He has occupied the Fulton-Watson-Copp chair in Computer Science at the University of Illinois since 2014. David published over 170 papers on computer vision, computer graphics and machine learning. In addition, David served as programme co-chair for IEEE Computer Vision and Pattern Recognition in 2000, 2011, 2018 and 2021, general co-chair for CVPR 2006 and 2015 and ICCV 2019, programme co-chair for the European Conference on Computer Vision 2008 and is a regular member of the programme committee of all major international conferences on computer vision. David also served six years on the SIGGRAPH programme committee and is a regular reviewer for that conference. He received best paper awards at the International Conference on Computer Vision and at the European Conference on Computer Vision, as well as an IEEE technical achievement award for 2005 for his research. David became an IEEE Fellow in 2009, and 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). Two further textbooks, “Probability and Statistics for Computer Science” and “Applied Machine Learning” are now in print. David served two terms as Editor in Chief, IEEE TPAMI, as well as a number of scientific advisory boards and have an active practise as an expert witness.