Show simple item record

dc.contributor.authorLeonard, Ludwicen_US
dc.contributor.authorHöhlein, Kevinen_US
dc.contributor.authorWestermann, Rüdigeren_US
dc.contributor.editorMitra, Niloy and Viola, Ivanen_US
dc.date.accessioned2021-04-09T08:00:02Z
dc.date.available2021-04-09T08:00:02Z
dc.date.issued2021
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.142623
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf142623
dc.description.abstractAccurate subsurface scattering solutions require the integration of optical material properties along many complicated light paths. We present a method that learns a simple geometric approximation of random paths in a homogeneous volume with translucent material. The generated representation allows determining the absorption along the path as well as a direct lighting contribution, which is representative of all scatter events along the path. A sequence of conditional variational auto-encoders (CVAEs) is trained to model the statistical distribution of the photon paths inside a spherical region in the presence of multiple scattering events. A first CVAE learns how to sample the number of scatter events, occurring on a ray path inside the sphere, which effectively determines the probability of this ray to be absorbed. Conditioned on this, a second model predicts the exit position and direction of the light particle. Finally, a third model generates a representative sample of photon position and direction along the path, which is used to approximate the contribution of direct illumination due to in-scattering. To accelerate the tracing of the light path through the volumetric medium toward the solid boundary, we employ a sphere-tracing strategy that considers the light absorption and can perform a statistically accurate next-event estimation. We demonstrate efficient learning using shallow networks of only three layers and no more than 16 nodes. In combination with a GPU shader that evaluates the CVAEs' predictions, performance gains can be demonstrated for a variety of different scenarios. We analyze the approximation error that is introduced by the data-driven scattering simulation and shed light on the major sources of error.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectRay tracing
dc.titleLearning Multiple-Scattering Solutions for Sphere-Tracing of Volumetric Subsurface Effectsen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersDeep Rendering
dc.description.volume40
dc.description.number2
dc.identifier.doi10.1111/cgf.142623
dc.identifier.pages165-178


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record