83 citations · 83 across the 1 of their papers we have counts for
3 papers
Neural Control Variates
Thomas Müller, Fabrice Rousselle, Jan Novák +1
We propose neural control variates (NCV) for unbiased variance reduction in parametric Monte Carlo integration. So far, the core challenge of applying the method of control variate…
Neural Importance Sampling
Thomas Müller, Brian McWilliams, Fabrice Rousselle +2
We propose to use deep neural networks for generating samples in Monte Carlo integration. Our work is based on non-linear independent components estimation (NICE), which we extend…
Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks
Simon Kallweit, Thomas Müller, Brian McWilliams +2
We present a technique for efficiently synthesizing images of atmospheric clouds using a combination of Monte Carlo integration and neural networks. The intricacies of Lorenz-Mie s…