deep learning, light transport covariance, perceptual loss, Monte Carlo denoising
Monte Carlo based methods such as path tracing are widely used in movie production. To achieve low noise, they require many samples per pixel, resulting in long rendering time. To reduce the cost, one solution is Monte Carlo denoising, which renders the image with fewer samples per pixel (as little as 128) and then denoises the resulting image. Many Monte Carlo denoising methods rely on deep learning: they use convolutional neural networks to learn the relationship between noisy images and reference images, using auxiliary features such as position and normal together with image color as inputs. The network predicts kernels which are then applied to the noisy input. These methods show powerful denoising ability, but tend to lose geometric or lighting details and to blur sharp features during denoising.
Tsinghua University Press
Weiheng Lin, Beibei Wang, Lu Wang et al. A detail preserving neural network model for Monte Carlo denoising. Computational Visual Media 2020, 6(2): 157-168.