And look like Researcher at Nvidia just make it happen. The good point about this is that it is fully dynamic. Meaning that you can move Camera Geometry light source without any headaches . Performance wize it is based on 3ms training wich extremelly low. It doesn't fear glossy rays.
We introduce a real-time neural radiance caching technique for path-traced global illumination. Our system is designed to handle fully dynamic scenes, and makes no assumptions about the lighting, geometry, and materials. The data-driven nature of our approach sidesteps many difficulties of caching algorithms, such as locating, interpolating, and updating cache points. Since pretraining neural networks to handle novel, dynamic scenes is a formidable generalization challenge, we do away with pretraining and instead achieve generalization via adaptation, i.e. we opt for training the radiance cache while rendering. We employ self-training—reminiscent of radiosity algorithms—to provide low-noise training targets and simulate infinite-bounce transport by merely iterating few-bounce training updates. The updates and cache queries incur a mild overhead—about 2.6ms on full HD resolution—thanks to a streaming implementation of the neural network that fully exploits modern hardware. We demonstrate significant noise reduction at the cost of little induced bias, and report state-of-the-art, real-time performance on a number of challenging scenarios.
VIDEO
https://d1qx31qr3h6wln.cloudfront.net/p ... -video.mp4
PAPER
https://d1qx31qr3h6wln.cloudfront.net/p ... aper_4.pdf