Show simple item record

dc.contributor.authorDeschaintre, Valentinen_US
dc.contributor.authorAittala, Miikaen_US
dc.contributor.authorDurand, Fredoen_US
dc.contributor.authorDrettakis, Georgeen_US
dc.contributor.authorBousseau, Adrienen_US
dc.contributor.editorBoubekeur, Tamy and Sen, Pradeepen_US
dc.description.abstractEmpowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph. Such lightweight capture is in stark contrast with the tens or hundreds of pictures required by traditional optimization-based approaches. However, a single image is often simply not enough to observe the rich appearance of realworld materials. We present a deep-learning method capable of estimating material appearance from a variable number of uncalibrated and unordered pictures captured with a handheld camera and flash. Thanks to an order-independent fusing layer, this architecture extracts the most useful information from each picture, while benefiting from strong priors learned from data. The method can handle both view and light direction variation without calibration. We show how our method improves its prediction with the number of input pictures, and reaches high quality reconstructions with as little as 1 to 10 images - a sweet spot between existing single-image and complex multi-image approaches.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectReflectance modeling
dc.subjectImage processing
dc.subjectMaterial capture
dc.subjectAppearance capture
dc.subjectDeep learning
dc.titleFlexible SVBRDF Capture with a Multi-Image Deep Networken_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersMaterials and Reflectance

Files in this item


This item appears in the following Collection(s)

  • 38-Issue 4
    Rendering 2019 - Symposium Proceedings

Show simple item record