Professor Dr. Sohaib Khan

(LUMS School of Technology, Lahore Pakistan)

"On Representing 3D Point Clouds"

Efficient representation of 3D point clouds is important for many computer graphics and computer vision applications. Time-varying point clouds are widely used in movies for performance animation, and character modeling. A variety of objects such as faces, bodies, or cloth, are often represented as collections of moving spatial landmarks. A compact and efficient model for representing point clouds not only leads to better compression, but is crucial for many inference tasks, such as estimating 3D structure from images, motion capture, noise removal, gap filling and motion editing.

In this talk, I will discuss our recent work on exploiting spatiotemporal redundancies in 3D point cloud data for efficient and compact representation. I will show how better models lead to more practical inference algorithms, and will also demonstrate the utility of this model for a series of exciting applications.

Bio: Sohaib Khan is Associate Professor and Department Chair of Computer Science at LUMS School of Science and Engineering, Lahore, Pakistan. His research interests broadly span the areas of image and video analysis, including estimating 3D from images, motion capture and multiple camera surveillance systems. Dr Khan earned his PhD degree in Computer Science in 2002 from University of Central Florida, specializing in computer vision. He was the associate editor of Machine Vision and Applications journal from 2008 - 2010. Dr Khan was awarded Hillman Award for Excellence in PhD Research in 2001 and Best Teacher Award by LUMS Computer Science Department in 2007.

More information about Dr Khan is available on his website at http://web.lums.edu.pk/~sohaib.

Zeit: Montag, 05.12.2011, 17.15 Uhr
Ort: Gebäude 48, Raum 210