Regularizing Image Reconstruction for Gradient-Domain Rendering with Feature Patches

dc.contributor.authorManzi, Marcoen_US
dc.contributor.authorVicini, Delioen_US
dc.contributor.authorZwicker, Matthiasen_US
dc.contributor.editorJoaquim Jorge and Ming Linen_US
dc.date.accessioned2016-04-26T08:38:29Z
dc.date.available2016-04-26T08:38:29Z
dc.date.issued2016en_US
dc.description.abstractWe present a novel algorithm to reconstruct high-quality images from sampled pixels and gradients in gradient-domain rendering. Our approach extends screened Poisson reconstruction by adding additional regularization constraints. Our key idea is to exploit local patches in feature images, which contain per-pixels normals, textures, position, etc., to formulate these constraints. We describe a GPU implementation of our approach that runs on the order of seconds on megapixel images. We demonstrate a significant improvement in image quality over screened Poisson reconstruction under the L1 norm. Because we adapt the regularization constraints to the noise level in the input, our algorithm is consistent and converges to the ground truth.en_US
dc.description.number2en_US
dc.description.sectionheadersRendering Techniquesen_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume35en_US
dc.identifier.doi10.1111/cgf.12829en_US
dc.identifier.issn1467-8659en_US
dc.identifier.pages263-273en_US
dc.identifier.urihttps://doi.org/10.1111/cgf.12829en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectI.3.3 [Computer Graphics]en_US
dc.subjectPicture/Image Generationen_US
dc.subjectDisplay Algorithmsen_US
dc.titleRegularizing Image Reconstruction for Gradient-Domain Rendering with Feature Patchesen_US
Files