题 目：A Surface Reflectance Model and its Applications in Image Sequences
讲 座 人：Dr.VeroniquePrinet (General Motors Advanced Technical Center, Israel)
主 持 人：Prof. Chunhong Pan
We estimate illuminant chromaticity from temporal sequences, for scenes illuminated by either one or two dominant illuminants. While there are many methods for illuminant estimation from a single image, few works so far have focused on videos, and even fewer on multiple light sources. Our aim is to leverage information provided by the temporal acquisition, where either the objects or the camera or the light source are/is in motion in order to estimate illuminant color without the need for user interaction or using strong assumptions and heuristics. We introduce a simple physically-based formulation based on the assumption that the incident light chromaticity is constant over a short space-time domain. We show that a deterministic approach is not sufficient for accurate and robust estimation: however, a probabilistic formulation makes it possible to implicitly integrate away hidden factors that have been ignored by the physical model. Experimental results are reported on a dataset of natural video sequences and on the GrayBall benchmark, indicating that we compare favorably with the state-of-the-art.
(This is a joint work with Dani Lischinski and Michael Werman)
Veronique Prinet is presently a Senior Researcher at General Motors Advanced Technical Center, Israel. She was an Associate Professor at the Institute of Automation, Chinese Academy of Sciences (CASIA) from 2000 to 2010. She spent two sabbatical years at the Hebrew University of Jerusalem, Israel, from 2011 to 2013.
Veronique received a B.Sc. degree in Physics from Univ. Paris-7 Jussieu (France), a M.Sc. in Biomedical Engineering from Univ. of Montreal (Canada) and Ph.D. in Computer Science (Image Processing) from INRIA (French National Institute in Computer Science and Automation), in collaboration with CNES (French National Center for Spatial Studies) and University Paris-11 Orsay. She took a a post-doctoral position at the National Lab. of Pattern Recognition, Chinese Academy of Science (Beijing)