The appearance of an object is greatly influenced by its surface materials as well as the surrounding illumination, and it is essential for computer vision tasks to be able to predict its variation. My colleagues and I have been working on modeling and predicting the complex appearance of real objects under natural illumination conditions. We especially developed image-based and inverse-lighting approaches to modeling real-world illumination and worked on modeling objects' reflectance solely from images taken under varying lighting conditions. In this talk, we introduce our contribution in inverse rendering for modeling real-world objects.
Imari Sato received the BS degree in policy management from Keio University in 1994. After studying at Robotics Institute of Carnegie Mellon University as a visiting scholar, she received the MS and PhD degrees in interdisciplinary Information Studies from the University of Tokyo in 2002 and 2005, respectively. In 2005, she joined the National Institute of Informatics, where she is currently an associate professor. Her primary research interests are in the fields of computer vision (physics-based vision, image-based modeling) and Computer Graphics (image-based rendering, augmented reality). She has received various research awards, including The Young Scientists'
Prize from The Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology (2009).