Learning Multiple-Scattering Solutions for Sphere-Tracing of Volumetric Subsurface Effects
| dc.contributor.author | Leonard, Ludwic | en_US |
| dc.contributor.author | Höhlein, Kevin | en_US |
| dc.contributor.author | Westermann, Rüdiger | en_US |
| dc.contributor.editor | Mitra, Niloy and Viola, Ivan | en_US |
| dc.date.accessioned | 2021-04-09T08:00:02Z | |
| dc.date.available | 2021-04-09T08:00:02Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | Accurate 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.description.number | 2 | |
| dc.description.sectionheaders | Deep Rendering | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 40 | |
| dc.identifier.doi | 10.1111/cgf.142623 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 165-178 | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.142623 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf142623 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | Computing methodologies | |
| dc.subject | Neural networks | |
| dc.subject | Ray tracing | |
| dc.title | Learning Multiple-Scattering Solutions for Sphere-Tracing of Volumetric Subsurface Effects | en_US |