Multiple Importance Sampling (MIS) combines several sampling techniques. Its weighting scheme depends on how many samples are generated with each particular method. This paper examines the optimal determination of the number of samples allocated to each of the combined techniques taking into account that this decision can depend only on a relatively small number of previous samples. The proposed method is demonstrated with the combination of BRDF sampling and Light source sampling, and we show that due to its robustness, it can outperform the theoretically more accurate approaches.
Multiple Importance Sampling, Sampling budget, Monte Carlo methods