MaterIA: Single Image High-Resolution Material Capture in the Wild

Simple item page
dc.contributor.authorMartin, Rosalieen_US
dc.contributor.authorRoullier, Arthuren_US
dc.contributor.authorRouffet, Romainen_US
dc.contributor.authorKaiser, Adrienen_US
dc.contributor.authorBoubekeur, Tamyen_US
dc.contributor.editorChaine, Raphaëlleen_US
dc.contributor.editorKim, Min H.en_US
dc.date.accessioned2022-04-22T06:27:35Z
dc.date.available2022-04-22T06:27:35Z
dc.date.issued2022
dc.description.abstractWe propose a hybrid method to reconstruct a physically-based spatially varying BRDF from a single high resolution picture of an outdoor surface captured under natural lighting conditions with any kind of camera device. Relying on both deep learning and explicit processing, our PBR material acquisition handles the removal of shades, projected shadows and specular highlights present when capturing a highly irregular surface and enables to properly retrieve the underlying geometry. To achieve this, we train two cascaded U-Nets on physically-based materials, rendered under various lighting conditions, to infer the spatiallyvarying albedo and normal maps. Our network processes relatively small image tiles (512x512 pixels) and we propose a solution to handle larger image resolutions by solving a Poisson system across these tiles. We complete this pipeline with analytical solutions to reconstruct height, roughness and ambient occlusion.en_US
dc.description.number2
dc.description.sectionheadersAppearance and Shading
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14466
dc.identifier.issn1467-8659
dc.identifier.pages163-177
dc.identifier.pages15 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14466
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14466
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titleMaterIA: Single Image High-Resolution Material Capture in the Wilden_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
v41i2pp163-177.pdf
Size:
240.7 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
paper1153_3.pdf
Size:
350.59 MB
Format:
Adobe Portable Document Format
Download
Collections
41-Issue 2