Guided Fine-Tuning for Large-Scale Material Transfer

dc.contributor.authorDeschaintre, Valentinen_US
dc.contributor.authorDrettakis, Georgeen_US
dc.contributor.authorBousseau, Adrienen_US
dc.contributor.editorDachsbacher, Carsten and Pharr, Matten_US
dc.date.accessioned2020-06-28T15:24:10Z
dc.date.available2020-06-28T15:24:10Z
dc.date.issued2020
dc.description.abstractWe present a method to transfer the appearance of one or a few exemplar SVBRDFs to a target image representing similar materials. Our solution is extremely simple: we fine-tune a deep appearance-capture network on the provided exemplars, such that it learns to extract similar SVBRDF values from the target image. We introduce two novel material capture and design workflows that demonstrate the strength of this simple approach. Our first workflow allows to produce plausible SVBRDFs of large-scale objects from only a few pictures. Specifically, users only need take a single picture of a large surface and a few close-up flash pictures of some of its details.We use existing methods to extract SVBRDF parameters from the close-ups, and our method to transfer these parameters to the entire surface, enabling the lightweight capture of surfaces several meters wide such as murals, floors and furniture. In our second workflow, we provide a powerful way for users to create large SVBRDFs from internet pictures by transferring the appearance of existing, pre-designed SVBRDFs. By selecting different exemplars, users can control the materials assigned to the target image, greatly enhancing the creative possibilities offered by deep appearance capture.en_US
dc.description.number4
dc.description.sectionheadersMaterials
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14056
dc.identifier.issn1467-8659
dc.identifier.pages91-105
dc.identifier.urihttps://doi.org/10.1111/cgf.14056
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14056
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectComputing methodologies
dc.subjectReflectance modeling
dc.subjectImage processing
dc.subjectKeywords
dc.subjectmaterial transfer
dc.subjectmaterial capture
dc.subjectappearance capture
dc.subjectSVBRDF
dc.subjectdeep learning
dc.subjectfine tuning
dc.titleGuided Fine-Tuning for Large-Scale Material Transferen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
v39i4pp091-105.pdf
Size:
54.94 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
supplementals.zip
Size:
599.81 MB
Format:
Zip file
Collections