Show simple item record

dc.contributor.authorCurrius, Roc Ramonen_US
dc.contributor.authorDolonius, Danen_US
dc.contributor.authorAssarsson, Ulfen_US
dc.contributor.authorSintorn, Eriken_US
dc.contributor.editorPanozzo, Daniele and Assarsson, Ulfen_US
dc.description.abstractWe 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 coherenten_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.subjectComputing methodologies
dc.subjectRay tracing
dc.titleSpherical Gaussian Light-field Textures for Fast Precomputed Global Illuminationen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersDeep Learning for Rendering

Files in this item


This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International License
Except where otherwise noted, this item's license is described as Attribution 4.0 International License