A Learned Radiance-Field Representation for Complex Luminaires

TL;DR

This paper introduces a neural radiance field-based method for efficiently rendering complex luminaires by encoding their light emission in an octree structure, enabling faster rendering with minimal quality loss.

Contribution

It presents a novel octree-based representation of luminaires using neural radiance fields, addressing high dynamic range and complex light paths for efficient rendering.

Findings

Achieves up to 100x speed-up in rendering complex luminaires

Maintains high visual quality with minimal error

Integrates seamlessly into traditional rendering systems

Abstract

We propose an efficient method for rendering complex luminaires using a high-quality octree-based representation of the luminaire emission. Complex luminaires are a particularly challenging problem in rendering, due to their caustic light paths inside the luminaire. We reduce the geometric complexity of luminaires by using a simple proxy geometry and encode the visually-complex emitted light field by using a neural radiance field. We tackle the multiple challenges of using NeRFs for representing luminaires, including their high dynamic range, high-frequency content and null-emission areas, by proposing a specialized loss function. For rendering, we distill our luminaires' NeRF into a Plenoctree, which we can be easily integrated into traditional rendering systems. Our approach allows for speed-ups of up to 2 orders of magnitude in scenes containing complex luminaires introducing minimal error.