About this document
Regression-Based Monte Carlo Integration: Corentin Salaün, Adrien Gruson, Binh-Son Hua, Toshiya Hachisuka, Gurprit Singh by Lordalbior is a document available to read on EtoBox.
The document presents a novel approach to Monte Carlo (MC) integration by utilizing regression-based estimators that fit non-constant model functions to sampled values, improving efficiency over traditional methods. This new estimator is shown to be at least as effective as conventional MC integration, with theoretical guarantees for variance reduction. The authors validate their method through experiments on light transport integrals, demonstrating significant error reduction and providing a practical algo
- Author
- Lordalbior
- Language
- EN