Novel denoising method generates sharper photorealistic images faster

Monte Carlo computational methods are behind many of the realistic images in games and movies. They automate the complexities in simulating the physics of lights and cameras to generate high-quality renderings from samples of diverse image features and scenes. But the process of Monte Carlo rendering is slow and can take hours—or even days—to produce a single image, and oftentimes the results are still pixelated, or "noisy."

* This article was originally published here