Path Sampling Methods for Differentiable Rendering

dc.contributor.authorSu, Tanlien_US
dc.contributor.authorGkioulekas, Ioannisen_US
dc.contributor.editorHaines, Ericen_US
dc.contributor.editorGarces, Elenaen_US
dc.date.accessioned2024-06-25T11:05:32Z
dc.date.available2024-06-25T11:05:32Z
dc.date.issued2024
dc.description.abstractWe introduce a suite of path sampling methods for differentiable rendering of scene parameters that do not induce visibility-driven discontinuities, such as BRDF parameters. We begin by deriving a path integral formulation for differentiable rendering of such parameters, which we then use to derive methods that importance sample paths according to this formulation. Our methods are analogous to path tracing and path tracing with next event estimation for primal rendering, have linear complexity, and can be implemented efficiently using path replay backpropagation. Our methods readily benefit from differential BRDF sampling routines, and can be further enhanced using multiple importance sampling and a loss-aware pixel-space adaptive sampling procedure tailored to our path integral formulation. We show experimentally that our methods reduce variance in rendered gradients by potentially orders of magnitude, and thus help accelerate inverse rendering optimization of BRDF parameters.en_US
dc.description.sectionheadersSampling
dc.description.seriesinformationEurographics Symposium on Rendering
dc.identifier.doi10.2312/sr.20241148
dc.identifier.isbn978-3-03868-262-2
dc.identifier.issn1727-3463
dc.identifier.pages13 pages
dc.identifier.urihttps://doi.org/10.2312/sr.20241148
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/sr20241148
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Ray tracing
dc.subjectCCS Concepts
dc.subjectComputing methodologies
dc.subject> Ray tracing
dc.titlePath Sampling Methods for Differentiable Renderingen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
03_sr20241148.pdf
Size:
25.18 MB
Format:
Adobe Portable Document Format