Show simple item record

dc.contributor.authorKavoosighafi, Behnazen_US
dc.contributor.authorFrisvad, Jeppe Revallen_US
dc.contributor.authorHajisharif, Saghien_US
dc.contributor.authorUnger, Jonasen_US
dc.contributor.authorMiandji, Ehsanen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWeidlich, Andreaen_US
dc.date.accessioned2023-06-27T06:41:39Z
dc.date.available2023-06-27T06:41:39Z
dc.date.issued2023
dc.identifier.isbn978-3-03868-229-5
dc.identifier.isbn978-3-03868-228-8
dc.identifier.issn1727-3463
dc.identifier.urihttps://doi.org/10.2312/sr.20231123
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/sr20231123
dc.description.abstractWe propose a novel dictionary-based representation learning model for Bidirectional Texture Functions (BTFs) aiming at compact storage, real-time rendering performance, and high image quality. Our model is trained once, using a small training set, and then used to obtain a sparse tensor containing the model parameters. Our technique exploits redundancies in the data across all dimensions simultaneously, as opposed to existing methods that use only angular information and ignore correlations in the spatial domain. We show that our model admits efficient angular interpolation directly in the model space, rather than the BTF space, leading to a notably higher rendering speed than in previous work. Additionally, the high quality-storage cost tradeoff enabled by our method facilitates controlling the image quality, storage cost, and rendering speed using a single parameter, the number of coefficients. Previous methods rely on a fixed number of latent variables for training and testing, hence limiting the potential for achieving a favorable quality-storage cost tradeoff and scalability. Our experimental results demonstrate that our method outperforms existing methods both quantitatively and qualitatively, as well as achieving a higher compression ratio and rendering speed.en_US
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 -> Rendering; Reflectance modeling; Machine learning approaches
dc.subjectComputing methodologies
dc.subjectRendering
dc.subjectReflectance modeling
dc.subjectMachine learning approaches
dc.titleSparseBTF: Sparse Representation Learning for Bidirectional Texture Functionsen_US
dc.description.seriesinformationEurographics Symposium on Rendering
dc.description.sectionheadersMaterials
dc.identifier.doi10.2312/sr.20231123
dc.identifier.pages37-50
dc.identifier.pages14 pages


Files in this item

Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

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