Show simple item record

dc.contributor.authorMukherjee, Sabyasachien_US
dc.contributor.authorMukherjee, Sayanen_US
dc.contributor.authorHua, Binh-Sonen_US
dc.contributor.authorUmetani, Nobuyukien_US
dc.contributor.authorMeister, Danielen_US
dc.contributor.editorZhang, Fang-Lue and Eisemann, Elmar and Singh, Karanen_US
dc.description.abstractMonte Carlo integration is a technique for numerically estimating a definite integral by stochastically sampling its integrand. These samples can be averaged to make an improved estimate, and the progressive estimates form a sequence that converges to the integral value on the limit. Unfortunately, the sequence of Monte Carlo estimates converges at a rate of O(pn), where n denotes the sample count, effectively slowing down as more samples are drawn. To overcome this, we can apply sequence transformation, which transforms one converging sequence into another with the goal of accelerating the rate of convergence. However, analytically finding such a transformation for Monte Carlo estimates can be challenging, due to both the stochastic nature of the sequence, and the complexity of the integrand. In this paper, we propose to leverage neural networks to learn sequence transformations that improve the convergence of the progressive estimates of Monte Carlo integration. We demonstrate the effectiveness of our method on several canonical 1D integration problems as well as applications in light transport simulation.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectMathematics of computing
dc.subjectNumerical analysis
dc.subjectProbability and statistics
dc.subjectComputing methodologies
dc.subjectMachine learning algorithms
dc.subjectRay tracing
dc.titleNeural Sequence Transformationen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersGlobal Illumination

Files in this item


This item appears in the following Collection(s)

  • 40-Issue 7
    Pacific Graphics 2021 - Symposium Proceedings

Show simple item record