Show simple item record

dc.contributor.authorInoue, Naotoen_US
dc.contributor.authorIto, Daichien_US
dc.contributor.authorHold-Geoffroy, Yannicken_US
dc.contributor.authorMai, Longen_US
dc.contributor.authorPrice, Brianen_US
dc.contributor.authorYamasaki, Toshihikoen_US
dc.contributor.editorPanozzo, Daniele and Assarsson, Ulfen_US
dc.date.accessioned2020-05-24T12:53:12Z
dc.date.available2020-05-24T12:53:12Z
dc.date.issued2020
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.13943
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13943
dc.description.abstractWe present RGB2AO, a novel task to generate ambient occlusion (AO) from a single RGB image instead of screen space buffers such as depth and normal. RGB2AO produces a new image filter that creates a non-directional shading effect that darkens enclosed and sheltered areas. RGB2AO aims to enhance two 2D image editing applications: image composition and geometryaware contrast enhancement. We first collect a synthetic dataset consisting of pairs of RGB images and AO maps. Subsequently, we propose a model for RGB2AO by supervised learning of a convolutional neural network (CNN), considering 3D geometry of the input image. Experimental results quantitatively and qualitatively demonstrate the effectiveness of our model.en_US
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.subjectImage
dc.subjectbased rendering
dc.titleRGB2AO: Ambient Occlusion Generation from RGB Imagesen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersImages and Videos
dc.description.volume39
dc.description.number2
dc.identifier.doi10.1111/cgf.13943
dc.identifier.pages451-462


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International License
Except where otherwise noted, this item's license is described as Attribution 4.0 International License