Gigapixel Imagery

Digital images have been around for so long now that we take them for granted. Yet while colored grids were convenient when television was being developed, they are now delaying the onset of perceptually saturating images. This project is a fundamental reexamination of the digital image, with the long-term goal of realizing real-time capture and synthesis of gigapixel imagery. We are inspired in our efforts by the human visual system, which creates continuous perception from the highly summarized output of 100 million rods and cones.

Principal Investigators: Ben Watson (NCSU CSC) & Jack Tumblin (NU CS).

Other project members: David Luebke (NVIDIA Research), Alex Kuhl (NCSU CSC), Li Yang (NCSU CSC), Dave Crist (NCSU CSC) & Jason Leyba (NCSU CSC).

Sponsors: NSF award 0646095, NVIDIA Professor Partnership

Publications

B.A. Watson. (2007). Higher-order image representations for hyper-resolution image synthesis and capture. Proc. SPIE/IS&T Human Vision and Electronic Imaging, Vol. 6492, W-1 – W-6. (pdf)

Leyba, J. (2007). Higher order primitives for the reconstruction of coarsely sampled imagery. (pdf)

B.A Watson & D. Luebke. (2005). The ultimate display: where will all the pixels come from? IEEE Computer, 38, 8, 54-61. (pdf)

Imagery

	Display, GPU & CPU comparison Display hardware is improving at disappointing rates.
	Display, GPU & CPU comparison Display hardware is improving at disappointing rates.