Adaptive sampling in Monte Carlo renderings using error-predicting neural networks

A computer product comprising a non-transitory computer readable medium storing a plurality of instructions that when executed control a computer system to render images by Monte Carlo (MC) path tracing, the instructions comprising:

• rendering, using a renderer, a first input image by MC path tracing, the first input image including a plurality of pixels and input color data for each pixel, the first input image rendered with a first number of samples across the plurality of pixels;
• generating a first denoised image corresponding to the first input image, the first denoised image including the plurality of pixels and denoised color data for each pixel;
• predicting a first sampling map using a first neural network, the first sampling map including the plurality of pixels, wherein the first neural network is configured to:
• receive the first input image and the first denoised image;
• and
• generate a respective error value for each respective pixel of the first sampling map, the respective error value relating to a difference between denoised color data and input color data for the respective pixel;
• and
• rendering, using the renderer, a second input image corresponding to the first input image by MC path tracing, the second input image including the plurality of pixels, the second input image rendered with a second number of samples greater than the first number, wherein the second number of samples is distributed across the plurality of pixels based on the first sampling map.