denoising

A Two Minute Papers episode on NVIDIA's recurrent denoising autoencoder, which cleans up noisy Monte Carlo path-traced image sequences. It shows how a neural network can produce usable renders from very few samples.

A short video accompanying the CVPR 2018 paper Learning to See in the Dark. It shows a neural network producing sharp images from very low-light raw sensor data, compared against denoising approaches.

Gamers Nexus builds a fully ray-traced demo in Unreal Engine to compare faked global illumination with RTX ray-traced GI. It covers the gains in dynamic scenes and accuracy against the performance cost and noise.