Exploiting Neighboring Pixels Similarity for Effective SV-BRDF Reconstruction from Sparse MLICs

dc.contributor.authorPintus, Ruggeroen_US
dc.contributor.authorAhsan, Moonisaen_US
dc.contributor.authorMarton, Fabioen_US
dc.contributor.authorGobbetti, Enricoen_US
dc.contributor.editorHulusic, Vedad and Chalmers, Alanen_US
dc.date.accessioned2021-11-02T08:55:49Z
dc.date.available2021-11-02T08:55:49Z
dc.date.issued2021
dc.description.abstractWe present a practical solution to create a relightable model from Multi-light Image Collections (MLICs) acquired using standard acquisition pipelines. The approach targets the difficult but very common situation in which the optical behavior of a flat, but visually and geometrically rich object, such as a painting or a bas relief, is measured using a fixed camera taking few images with a different local illumination. By exploiting information from neighboring pixels through a carefully crafted weighting and regularization scheme, we are able to efficiently infer subtle per-pixel analytical Bidirectional Reflectance Distribution Functions (BRDFs) representations from few per-pixel samples. The method is qualitatively and quantitatively evaluated on both synthetic data and real paintings in the scope of image-based relighting applications.en_US
dc.description.sectionheadersReconstruction
dc.description.seriesinformationEurographics Workshop on Graphics and Cultural Heritage
dc.identifier.doi10.2312/gch.20211412
dc.identifier.isbn978-3-03868-141-0
dc.identifier.issn2312-6124
dc.identifier.pages103-112
dc.identifier.urihttps://doi.org/10.2312/gch.20211412
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/gch20211412
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectAppearance and texture representations
dc.subjectReflectance modeling
dc.subjectScene understanding
dc.titleExploiting Neighboring Pixels Similarity for Effective SV-BRDF Reconstruction from Sparse MLICsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
103-112.pdf
Size:
6.14 MB
Format:
Adobe Portable Document Format