Image and Video-Based Modeling and Rendering

Richard Szeliski
Microsoft Research

Time and Place

1305 Newell-Simon Hall
Refreshments 3:15 pm
Talk 3:30 pm

Abstract

Interactive Visual Media Group Microsoft Research Obtaining photo-realistic geometric and photometric models is an important component of image-based rendering systems that use real-world imagery as their input. Applications of such systems include novel view generation and the mixing of live imagery with synthetic computer graphics. In this talk, I review a number of image-based rendering systems and discuss some of the representations that they use. I then focus on one particular open problem in image based modeling, namely the treatment of reflections and specularities, and show some of our recent results in this area. I will also present our work in video-based rendering, in which we synthesize novel video from short sample clips by discovering their (quasi-repetive) temporal structure. Image-based and video-based rendering can be combined to create compelling photorealistic interactive experiences. I will demonstrate some of these experiences with a particular focus on visiting remote sites of interest, i.e., Virtual Tourism. About the Speaker

Speaker Biography

Dr. Szeliski has published over 80 research papers in computer vision, computer graphics, medical imaging, and neural nets, as well as the book Bayesian Modeling of Uncertainty in Low-Level Vision. He was a Program Committee Chair for ICCV'2001, and is on the Editorial Board of the International Journal of Computer Vision. He has served as co-chair of the SPIE Conferences on Geometric Methods in Computer Vision, the 1999 Vision Algorithms Workshop, and as an Associate Editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence.

Speaker Appointments

For appointments, please contact Jianbo Shi (jshi@cs.cmu.edu).