Improving the sample efficiency of reinforcement learning algorithms to scale up to larger and more realistic domains is a current research challenge in machine learning. Model-ba...
A large class of stochastic optimization problems can be modeled as minimizing an objective function f that depends on a choice of a vector x ∈ X, as well as on a random external...
We present a lighting method for outdoor scenes with vegetation. The method is compatible with multiresolution trees generated using random L-systems. We include a sky dome model ...
This paper presents a stochastic iteration algorithm solving the global illumination problem, where the random sampling is governed by classical importance sampling and also by th...
Most face recognition systems only work well under quite constrained environments. In particular, the illumination conditions, facial expressions and head pose must be tightly con...