Show simple item record

dc.contributor.authorMazlov, Ilyaen_US
dc.contributor.authorMerzbach, Sebastianen_US
dc.contributor.authorTrunz, Elenaen_US
dc.contributor.authorKlein, Reinharden_US
dc.contributor.editorKlein, Reinhard and Rushmeier, Hollyen_US
dc.date.accessioned2019-09-11T09:10:52Z
dc.date.available2019-09-11T09:10:52Z
dc.date.issued2019
dc.identifier.isbn978-3-03868-080-2
dc.identifier.issn2309-5059
dc.identifier.urihttps://doi.org/10.2312/mam.20191311
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/mam20191311
dc.description.abstractAppearance acquisition is a challenging problem. Existing approaches require expensive hardware and acquisition times are long. Alternative ''in-the-wild'' few-shot approaches provide a limited reconstruction quality. Furthermore, there is a fundamental tradeoff between spatial resolution and the physical sample dimensions that can be captured in one measurement. In this paper, we investigate how neural texture synthesis and neural style transfer approaches can be applied to generate new materials with high spatial resolution from high quality SVBRDF measurements. We perform our experiments on a new database of measured SVBRDFs.en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectI.3.7 [Computer Graphics]
dc.subjectThree Dimensional Graphics and Realism
dc.subjectColor
dc.subjectshading
dc.subjectshadowing
dc.subjectand texture
dc.titleNeural Appearance Synthesis and Transferen_US
dc.description.seriesinformationWorkshop on Material Appearance Modeling
dc.description.sectionheadersPerception, Neural Methods, and Research Needs
dc.identifier.doi10.2312/mam.20191311
dc.identifier.pages35-39


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record