Abstract:

Digital Photograph and video are now ubiquitous in our everyday life. However, they capture only a 2D projection of our 3D world. The central theme of my research is how to effectively acquire and visualize objects in 3D. In this talk, I will present several approaches for 3D modeling, from real-time automatic reconstruction of static scenes to stitching partial height maps to a complete space-time model. In particular, I will present a new method that combines 3D reconstruction with physically-based simulation. This marriage is mutually beneficial: physically-based simulation can help identify outliers in 3D reconstruction and fill in the missing part in a plausible way; and 3D information from reconstruction removes the needs to manually set up simulation parameters. Applying this principle to dynamic fluid modeling shows that visually pleasing results can be obtained from as few as one pair of video cameras. If time permit, I will also show some results of motion capture from a single depth sensor. Since all of these techniques require only a single video or depth augmented video stream as input, We envision that they could be adopted in the future to allow everyone to capture and re-experience real-world events in interactive 3D.

   Biography：

Ruigang Yang received the MS degree in Computer Science from Columbia University in 1998 and the PhD degree in Computer Science from the University of North Carolina, Chapel Hill, in 2003. He is an Associate Professor in the Computer Science Department, University of Kentucky, currently at sabbatical at ETH-Zurich. His research interests include computer vision, computer graphics, and multimedia. He is a member of the IEEE Computer Society and the ACM. He is a recipient of NSF Faculty Early Career Development (CAREER) Program Award in 2004. 

Dr. Yang has published over 70 papers. These papers, according to Google Scholar, have received over 900 citations.  He has been in the program committees in most international conferences in computer vision, including ICCV, CVPR, and ECCV. He is an associate editor of the internal Journal of Machine Vision and Applications. He is an Area Chair for CVPR 2011 and a program co-chair for 3DIM/3DPVT in 2011.