Condor, JorgeJarabo, AdriánGhosh, AbhijeetWei, Li-Yi2022-07-012022-07-012022978-3-03868-187-81727-3463https://doi.org/10.2312/sr.20221155https://diglib.eg.org:443/handle/10.2312/sr20221155We 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 visuallycomplex 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.Attribution 4.0 International LicenseCCS Concepts: Computer graphics --> Neural Rendering; Machine Learning --> Neural Radiance FieldsComputer graphicsNeural RenderingMachine LearningNeural Radiance Fields10.2312/sr.2022115549-5810 pages