Spherical Gaussian Light-field Textures for Fast Precomputed Global Illumination

• Paper (PDF)
• https://doi.org/10.1111/cgf.13918 (DOI)
• https://www.youtube.com/watch?v=DWdYOFqlSZg (Video demonstration)
• https://gitlab.com/ror3d/spherical-gaussian-lightfields (Code implementation)
• https://www.youtube.com/live/qNRkYMTppk0?t=51 (Video of the paper presentation)

Abstract

We describe a method to use Spherical Gaussians with free directions and arbitrary sharpness and amplitude to approximate the precomputed local light field for any point on a surface in a scene. This allows for a high-quality reconstruction of these light fields in a manner that can be used to render the surfaces with precomputed global illumination in real-time with very low cost both in memory and performance. We also extend this concept to represent the illumination-weighted environment visibility, allowing for high-quality reflections of the distant environment with both surface-material properties and visibility taken into account. We treat obtaining the Spherical Gaussians as an optimization problem for which we train a Convolutional Neural Network to produce appropriate values for each of the Spherical Gaussians' parameters. We define this CNN in such a way that the produced parameters can be interpolated between adjacent local light fields while keeping the illumination in the intermediate points coherent.

BibTex

@article{SphericalGaussianGlobalIllum:currius:2020,
    author = {Currius, Roc R. and Dolonius, Dan and Assarsson, Ulf and Sintorn, Erik},
    year = {2020},
    month = {05},
    pages = {133-146},
    title = {Spherical Gaussian Light‐field Textures for Fast Precomputed Global Illumination},
    volume = {39},
    journal = {Computer Graphics Forum},
    doi = {10.1111/cgf.13918}
}