Show simple item record

dc.contributor.authorWeier, Philippeen_US
dc.contributor.authorDroske, Marcen_US
dc.contributor.authorHanika, Johannesen_US
dc.contributor.authorWeidlich, Andreaen_US
dc.contributor.authorVorba, Jiríen_US
dc.contributor.editorBousseau, Adrien and McGuire, Morganen_US
dc.date.accessioned2021-07-12T12:09:15Z
dc.date.available2021-07-12T12:09:15Z
dc.date.issued2021
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14347
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14347
dc.description.abstractWe present Optimised Path Space Regularisation (OPSR), a novel regularisation technique for forward path tracing algorithms. Our regularisation controls the amount of roughness added to materials depending on the type of sampled paths and trades a small error in the estimator for a drastic reduction of variance in difficult paths, including indirectly visible caustics. We formulate the problem as a joint bias-variance minimisation problem and use differentiable rendering to optimise our model. The learnt parameters generalise to a large variety of scenes irrespective of their geometric complexity. The regularisation added to the underlying light transport algorithm naturally allows us to handle the problem of near-specular and glossy path chains robustly. Our method consistently improves the convergence of path tracing estimators, including state-of-the-art path guiding techniques where it enables finding otherwise hard-to-sample paths and thus, in turn, can significantly speed up the learning of guiding distributions.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectRendering
dc.titleOptimised Path Space Regularisationen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersPath Tracing, Monte Carlo Rendering
dc.description.volume40
dc.description.number4
dc.identifier.doi10.1111/cgf.14347
dc.identifier.pages139-151


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • 40-Issue 4
    Rendering 2021 - Symposium Proceedings

Show simple item record