Neural Two-Level Monte Carlo Real-Time Rendering

TL;DR

This paper presents a novel real-time rendering method combining a neural radiance cache with a two-level Monte Carlo estimator, enabling faster convergence and noise reduction in global illumination rendering without scene assumptions.

Contribution

It introduces Neural Incident Radiance Cache (NIRC) and a two-level Monte Carlo estimator for efficient, scene-agnostic real-time rendering with on-line training and dynamic scene support.

Findings

NIRC evaluation is 2-25x faster than path tracing.

Method achieves faster convergence and noise reduction.

No assumptions about scene geometry, materials, or lighting.

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 fully-fused tiny neural networks 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 2-25x 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 importance sampling schemes and noise reduction techniques.