Disney Research has posted a paper proposing a method for rendering atmospheric clouds with radiance predicting neural networks. According to their abstract, this is achieved by “using a combination of Monte Carlo integration and neural networks. The intricacies of Lorenz-Mie scattering and the high albedo of cloud-forming aerosols make rendering of clouds—e.g. the characteristic silver lining and the “whiteness” of the inner body—challenging for methods based solely on Monte Carlo integration or diffusion theory.We approach the problem differently. Instead of simulating all light transport during rendering, we pre-learn the spatial and directional distribution of radiant flux from tens of cloud exemplars”. You can read the paper in full on the Disney Research website and see a video demonstration on YouTube.