Learning Multiple-Scattering Solutions for Sphere-Tracing of Volumetric Subsurface Effects

TL;DR

This paper introduces a learning-based method using conditional variational auto-encoders to approximate complex subsurface scattering paths in volumetric materials, enabling faster and accurate rendering of translucent effects.

Contribution

It presents a novel approach that models photon paths with CVAEs for efficient subsurface scattering simulation, improving speed while maintaining accuracy.

Findings

Efficient learning with shallow neural networks of three layers.

Significant performance gains in volumetric rendering scenarios.

Analysis of approximation errors in data-driven scattering simulation.

Abstract

Accurate subsurface scattering solutions require the integration of optical material properties along many complicated light paths. We present a method that learns a simple geometric approximation of random paths in a homogeneous volume of translucent material. The generated representation allows determining the absorption along the path as well as a direct lighting contribution, which is representative of all scattering events along the path. A sequence of conditional variational auto-encoders (CVAEs) is trained to model the statistical distribution of the photon paths inside a spherical region in presence of multiple scattering events. A first CVAE learns to sample the number of scattering events, occurring on a ray path inside the sphere, which effectively determines the probability of the ray being absorbed. Conditioned on this, a second model predicts the exit position and direction of the light particle. Finally, a third model generates a representative sample of photon position and direction along the path, which is used to approximate the contribution of direct illumination due to in-scattering. To accelerate the tracing of the light path through the volumetric medium toward the solid boundary, we employ a sphere-tracing strategy that considers the light absorption and is able to perform statistically accurate next-event estimation. We demonstrate efficient learning using shallow networks of only three layers and no more than 16 nodes. In combination with a GPU shader that evaluates the CVAEs' predictions, performance gains can be demonstrated for a variety of different scenarios. A quality evaluation analyzes the approximation error that is introduced by the data-driven scattering simulation and sheds light on the major sources of error in the accelerated path tracing process.