Deep Radiance Caching: Convolutional Autoencoders Deeper in Ray Tracing

TL;DR

Deep Radiance Caching (DRC) leverages convolutional autoencoders to efficiently render global illumination on CPU, supporting diverse materials without scene-specific training, enabling faster and more accessible realistic image synthesis.

Contribution

Introduces DRC, a novel radiance caching method using convolutional autoencoders that supports various materials without pre-training or scene-specific data.

Findings

Produces high-quality images within 180 seconds on CPU

Supports a wide range of material types

No offline pre-computation required

Abstract

Rendering realistic images with global illumination is a computationally demanding task and often requires dedicated hardware for feasible runtime. Recent research uses Deep Neural Networks to predict indirect lighting on image level, but such methods are commonly limited to diffuse materials and require training on each scene.We present Deep Radiance Caching (DRC), an efficient variant of Radiance Caching utilizing Convolutional Autoencoders for rendering global illumination. DRC employs a denoising neural network with Radiance Caching to support a wide range of material types, without the requirement of offline pre-computation or training for each scene.This offers high performance CPU rendering for maximum accessibility. Our method has been evaluated on interior scenes, and is able to produce high-quality images within 180 seconds on a single CPU.