Abstract:
Vision-based techniques have increasingly become common to provide realism in computer graphics. Image-based modeling, relighting, and rendering is a popular area that exemplifies this paradigm.
This talk has two components. First, in a tutorial vein, I provide a few examples of the use of image based techniques for computer graphics. Later, I discuss camera walks using light fields where once authentic imagery has been acquired using a camera gantry, or a handheld camera, detailed novel views can be synthetically generated from various viewpoints.
Specifically, when a user "walks'' through a virtual world, only a subset of the previously stored light field is required. Appropriate portions of the light field can then be cached at select ``nodal points'' that depend on the camera walk. Once spartanly and quickly cached, scenes can be rendered from any point on the walk efficiently.
About the speaker:
Sharat Chandran (http://www.cse.iitb.ac.in/~sharat) holds a doctorate in Computer Science from the University of Maryland (1989) and an undergraduate degree in Electrical and Electronics Engineering from the Indian Institute of Technology, Bombay (1984).
He has held academic or engineering appointments at the Indian Institute of Technology, Bombay; University of Maryland, College Park (USA); Stanford University, California (USA), Oracle Corporation, Redwood Shores (USA), NTT (Japan), and Schlumberger Corporation, Austin (USA).
Sharat's research interests are in computer graphics and vision, and in parallel computation. In these fields he has made noteworthy contributions in the form of archival journal articles and peer reviewed conference publications. About 30 students have graduated at the Masters level or higher under his supervision; a similar number of students have graduated with an undergraduate "honors" degree.
