A Learned Radiance-Field Representation for Complex Luminaires
| Autor: | Condor, Jorge, Jarabo, Adrián |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | Proceedings of the Eurographics Symposium on Rendering (2022), The Eurographics Association |
| Druh dokumentu: | Working Paper |
| DOI: | 10.2312/sr.20221155 |
| Popis: | 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. Comment: 10 pages, 7 figures. Eurographics Proceedings (EGSR 2022, Symposium-only track) (https://diglib.eg.org/handle/10.2312/sr20221155) |
| Databáze: | arXiv |
| Externí odkaz: |
|