Talk on Processing and Rendering Gigapixel Images and Videos

Loading Events

« All Events

  • This event has passed.

Talk on Processing and Rendering Gigapixel Images and Videos

March 8 @ 3:00 pm - 4:30 pm

Talk on Processing and Rendering Gigapixel Images and Videos

A special talk on Processing and Rendering Gigapixel Images and Videos will be delivered by Dr. Pedro Sander, Department of Computer Science Engineering, Hong Kong University of Science and Technology (HKUST), on 8th March 2019  from 15:00-16:30 hours at the Milton E.Bender Auditorium.

Abstract:
In this talk Dr. Pedro Sander will present his work on gigapixel images and videos. He will first discuss the technical challenges for creating gigantic panoramas, including our world record images of Rio de Janeiro. Then, he will present in more detail the first technique to create wide-angle, high-resolution looping panoramic videos. Starting with a 2D grid of registered videos acquired on a robotic mount, our method determines for each output pixel the source video and looping parameters that jointly maximize spatiotemporal consistency. The optimization is accelerated by reducing the set of source labels using a graph-coloring scheme. He parallelizes the computation and implement it out-of-core by partitioning the domain along low-importance paths. The merged panorama is assembled using gradient-domain blending and stored as a hierarchy of video tiles. Finally, an interactive viewer adaptively preloads these tiles for responsive browsing and allows the user to interactively edit and improve local regions. He will demonstrate these techniques on gigapixel-sized looping panoramas.
Bio:
Pedro V. Sander is an Associate Professor and the current Undergraduate Programs Director in the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology. His research interests span multiple areas of computer graphics and vision, mostly focusing on real-time rendering, graphics hardware, geometry processing, and recently imaging. He received a B.S. in Computer Science from Stony Brook University in 1998, and S.M. and Ph.D. degrees from Harvard University in 1999 and 2003, respectively. He was a senior member of the Application Research Group of ATI Research, where he conducted real-time rendering and general-purpose computation research with latest generation and upcoming graphics hardware. He then moved to academia, joining the Hong Kong to join the Faculty of the Hong Kong University of Science and Technology. He has served regularly in the ACM SIGGRAPH and ACM SIGGRAPH Asia paper committees, was the chair of the Courses program for ACM SIGGRAPH Asia 2011, and papers chair of the top and rendering conferences I3D and EGSR.


Details

Date:
March 8
Time:
3:00 pm - 4:30 pm

Venue

Milton E. Bender Jr. Auditorium Asian Institute of Technology (AIT)

Asian Institute of Technology

Klong Luang,,

Pathum Thani

12120

Thailand

+ Google Map