Show simple item record

dc.contributor.authorSchüßler, Vincenten_US
dc.contributor.authorHanika, Johannesen_US
dc.contributor.authorJung, Alisaen_US
dc.contributor.authorDachsbacher, Carstenen_US
dc.contributor.editorGhosh, Abhijeeten_US
dc.contributor.editorWei, Li-Yien_US
dc.date.accessioned2022-07-01T15:36:39Z
dc.date.available2022-07-01T15:36:39Z
dc.date.issued2022
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14582
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14582
dc.description.abstractGood importance sampling strategies are decisive for the quality and robustness of photorealistic image synthesis with Monte Carlo integration. Path guiding approaches use transport paths sampled by an existing base sampler to build and refine a guiding distribution. This distribution then guides subsequent paths in regions that are otherwise hard to sample. We observe that all terms in the measurement contribution function sampled during path construction depend on at most three consecutive path vertices. We thus propose to build a 9D guiding distribution over vertex triplets that adapts to the full measurement contribution with a 9D Gaussian mixture model (GMM). For incremental path sampling, we query the model for the last two vertices of a path prefix, resulting in a 3D conditional distribution with which we sample the next vertex along the path. To make this approach scalable, we partition the scene with an octree and learn a local GMM for each leaf separately. In a learning phase, we sample paths using the current guiding distribution and collect triplets of path vertices. We resample these triplets online and keep only a fixed-size subset in reservoirs. After each progression, we obtain new GMMs from triplet samples by an initial hard clustering followed by expectation maximization. Since we model 3D vertex positions, our guiding distribution naturally extends to participating media. In addition, the symmetry in the GMM allows us to query it for paths constructed by a light tracer. Therefore our method can guide both a path tracer and light tracer from a jointly learned guiding distribution.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies --> Ray tracing
dc.subjectComputing methodologies
dc.subjectRay tracing
dc.titlePath Guiding with Vertex Triplet Distributionsen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersGlobal Illumination
dc.description.volume41
dc.description.number4
dc.identifier.doi10.1111/cgf.14582
dc.identifier.pages1-15
dc.identifier.pages15 pages


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • 41-Issue 4
    Rendering 2022 - Symposium Proceedings

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