A Data-Driven Paradigm for Precomputed Radiance Transfer

Simple item page
dc.contributor.authorBelcour, Laurenten_US
dc.contributor.authorDeliot, Thomasen_US
dc.contributor.authorBarbier, Wilhemen_US
dc.contributor.authorSoler, Cyrilen_US
dc.contributor.editorJosef Spjuten_US
dc.contributor.editorMarc Stammingeren_US
dc.contributor.editorVictor Zordanen_US
dc.date.accessioned2023-01-23T10:23:44Z
dc.date.available2023-01-23T10:23:44Z
dc.date.issued2022
dc.description.abstractIn this work, we explore a change of paradigm to build Precomputed Radiance Transfer (PRT) methods in a data-driven way. This paradigm shift allows us to alleviate the difficulties of building traditional PRT methods such as defining a reconstruction basis, coding a dedicated path tracer to compute a transfer function, etc. Our objective is to pave the way for Machine Learned methods by providing a simple baseline algorithm. More specifically, we demonstrate real-time rendering of indirect illumination in hair and surfaces from a few measurements of direct lighting.We build our baseline from pairs of direct and indirect illumination renderings using only standard tools such as Singular Value Decomposition (SVD) to extract both the reconstruction basis and transfer function.en_US
dc.description.number3
dc.description.sectionheadersGraphics Systems
dc.description.seriesinformationProceedings of the ACM on Computer Graphics and Interactive Techniques
dc.description.volume5
dc.identifier.doi10.1145/3543864
dc.identifier.issn2577-6193
dc.identifier.urihttps://doi.org/10.1145/3543864
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1145/3543864
dc.publisherACM Association for Computing Machineryen_US
dc.subjectCCS Concepts: Computing methodologies -> Rendering Additional Key Words and Phrases: Real-time Rendering, Precomputed Radiance Transfer
dc.subjectComputing methodologies
dc.subjectRendering Additional Key Words and Phrases
dc.subjectReal
dc.subjecttime Rendering
dc.subjectPrecomputed Radiance Transfer
dc.titleA Data-Driven Paradigm for Precomputed Radiance Transferen_US
Files
Collections
High-Performance Graphics 2022