Neural Two‐Level Monte Carlo Real‐Time Rendering
Open Access
- 18 April 2025
- journal article
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (2)
Abstract
We introduce an efficient Two‐Level Monte Carlo (subset of Multi‐Level Monte Carlo, MLMC) estimator for real‐time rendering of scenes with global illumination. Using MLMC we split the shading integral into two parts: the radiance cache integral and the residual error integral that compensates for the bias of the first one. For the first part, we developed the Neural Incident Radiance Cache (NIRC) leveraging the power of tiny neural networks [MRNK21] as a building block, which is trained on the fly. The cache is designed to provide a fast and reasonable approximation of the incident radiance: an evaluation takes 2–25 × less compute time than a path tracing sample. This enables us to estimate the radiance cache integral with a high number of samples and by this achieve faster convergence. For the residual error integral, we compute the difference between the NIRC predictions and the unbiased path tracing simulation. Our method makes no assumptions about the geometry, materials, or lighting of a scene and has only few intuitive hyper‐parameters. We provide a comprehensive comparative analysis in different experimental scenarios. Since the algorithm is trained in an on‐line fashion, it demonstrates significant noise level reduction even for dynamic scenes and can easily be combined with other noise reduction techniques.Keywords
This publication has 31 references indexed in Scilit:
- NEnv: Neural Environment Maps for Global IlluminationComputer Graphics Forum, 2023
- Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields2022
- Multilevel Monte Carlo methodsActa Numerica, 2015
- Progressive photon mappingACM Transactions on Graphics, 2008
- Radiance Caching for Efficient Global Illumination ComputationIEEE Transactions on Visualization and Computer Graphics, 2005
- Safe and Effective Importance SamplingJournal of the American Statistical Association, 2000
- The irradiance volumeIEEE Computer Graphics and Applications, 1998
- Global Illumination using Photon Maps1996
- Optimally combining sampling techniques for Monte Carlo rendering1995
- The rendering equation1986