Monday, December 27, 2010

Global illumination with Markov Chain Monte Carlo rendering in Nvidia Optix 2.1 + Metropolis Light Transport with participating media on GPUs

Optix 2.1 was released a few days ago and includes a Markov Chain Monte Carlo (MCMC) sample, which only works on Fermi cards (New sample: MCMC - Markov Chain Monte Carlo method rendering. A global illumination solution that requires an SM 2.0 class device (e.g. Fermi) or higher).

MCMC rendering methods, such as MLT (Metropolis light transport) and ERPT (energy redistribution path tracing) are partially sequential because each path of a Markov chain depends on the previous path and is therefor more difficult to parallellize for GPUs than standard Monte Carlo algorithms. This is an image of the new MCMC sampler included in the new Optix SDK, which can be downloaded from http://developer.nvidia.com/object/optix-download.html.




There is also an update on the Kelemen-style Metropolis Light Transport GPU renderer from Dietger van Antwerpen. He has released this new video showing Metropolis light transport with participating media running on the GPU: http://www.youtube.com/watch?v=3Xo0qVT3nxg



This scene is straight from the original Metropolis light transport paper from Veach and Guibas (http://graphics.stanford.edu/papers/metro/metro.pdf). Participating media (like fog, smoke and god rays) are one of the most difficult and compute intensive phenomena to simulate accurately with global illumination, because it is essentially a volumetric effect in which light scattering occurs. Subsurface scattering belongs to the same category of expensive difficult-to-render volumetric effects. The video shows it can now be done in almost real-time with MLT. which is pretty impressive!

2 comments:

Samual said...

Its a really wonderful Blog. With regards to effectiveness, LED grow light triumph yet again. Plants are actually only capable of using 10% of the powerfully bright light that HID bulbs radiate.

Sam Lapere said...

Man, those plants are really power-inefficient creatures, they could learn a lesson or two from ARM I suppose. Thanks for the nice spam Samual!