Estimate an integral by averaging the integrand over random samples divided by their density. Converges as the inverse square root of sample count regardless of dimensionality, which is why it wins in path space.
supersedescorrects · extends
classifiesspecializes · part-of
substitutes forapproximates · alternative-to
depends onrequires · validates
Colour is the family; a dashed line is the second member of it.
Drag to pan · scroll to zoom · click a node to open it
Referenced by
correctsBilateral Filter fixes a defect in thistrades a little bias for a large drop in variance
correctsBlue-Noise Error Distribution fixes a defect in thissame error, redistributed to where the eye sees it least
correctsFirefly Clamping fixes a defect in thisrare huge samples never average away in practice
correctsImportance Sampling fixes a defect in thisuniform samples are wasted where the integrand is small
specializesPath Tracing is a specific case of thisthe sample space is the space of light paths
alternative-toQuasi-Monte Carlo is a competing approach to thisdeterministic even coverage converges faster
correctsStratified Sampling fixes a defect in thisindependent random samples clump and leave gaps
requiresVariational Autoencoder does not work without thisthe bound is estimated by sampling the latent