Spherical Gaussian Light-field Textures for Fast Precomputed Global Illumination
| dc.contributor.author | Currius, Roc Ramon | en_US |
| dc.contributor.author | Dolonius, Dan | en_US |
| dc.contributor.author | Assarsson, Ulf | en_US |
| dc.contributor.author | Sintorn, Erik | en_US |
| dc.contributor.editor | Panozzo, Daniele and Assarsson, Ulf | en_US |
| dc.date.accessioned | 2020-05-24T12:51:00Z | |
| dc.date.available | 2020-05-24T12:51:00Z | |
| dc.date.issued | 2020 | |
| dc.description.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 | en_US |
| dc.description.number | 2 | |
| dc.description.sectionheaders | Deep Learning for Rendering | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 39 | |
| dc.identifier.doi | 10.1111/cgf.13918 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 133-146 | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.13918 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf13918 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | Computing methodologies | |
| dc.subject | Rendering | |
| dc.subject | Ray tracing | |
| dc.title | Spherical Gaussian Light-field Textures for Fast Precomputed Global Illumination | en_US |