Show simple item record

dc.contributor.authorKT, Aakashen_US
dc.contributor.authorJarabo, Adrianen_US
dc.contributor.authorAliaga, Carlosen_US
dc.contributor.authorChiang, Matt Jen-Yuanen_US
dc.contributor.authorMaury, Olivieren_US
dc.contributor.authorHery, Christopheen_US
dc.contributor.authorNarayanan, P. J.en_US
dc.contributor.authorNam, Giljooen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWeidlich, Andreaen_US
dc.date.accessioned2023-06-27T07:04:18Z
dc.date.available2023-06-27T07:04:18Z
dc.date.issued2023
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14895
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14895
dc.description.abstractEfficiently and accurately rendering hair accounting for multiple scattering is a challenging open problem. Path tracing in hair takes long to converge while other techniques are either too approximate while still being computationally expensive or make assumptions about the scene. We present a technique to infer the higher order scattering in hair in constant time within the path tracing framework, while achieving better computational efficiency. Our method makes no assumptions about the scene and provides control over the renderer's bias & speedup. We achieve this by training a small multilayer perceptron (MLP) to learn the higher-order radiance online, while rendering progresses. We describe how to robustly train this network and thoroughly analyze our resulting renderer's characteristics. We evaluate our method on various hairstyles and lighting conditions. We also compare our method against a recent learning based & a traditional real-time hair rendering method and demonstrate better quantitative & qualitative results. Our method achieves a significant improvement in speed with respect to path tracing, achieving a run-time reduction of 40%-70% while only introducing a small amount of bias.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies -> Ray tracing; Parametric curve and surface models; Volumetric models
dc.subjectComputing methodologies
dc.subjectRay tracing
dc.subjectParametric curve and surface models
dc.subjectVolumetric models
dc.titleAccelerating Hair Rendering by Learning High-Order Scattered Radianceen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersScatter
dc.description.volume42
dc.description.number4
dc.identifier.doi10.1111/cgf.14895
dc.identifier.pages13 pages


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • 42-Issue 4
    Rendering 2023 - Symposium Proceedings

Show simple item record