Efficient Variational Light Field View Synthesis For Making Stereoscopic 3D Images

dc.contributor.authorZhang, Leien_US
dc.contributor.authorZhang, Yu-Hangen_US
dc.contributor.authorHuang, Huaen_US
dc.contributor.editorStam, Jos and Mitra, Niloy J. and Xu, Kunen_US
dc.date.accessioned2015-10-07T05:12:21Z
dc.date.available2015-10-07T05:12:21Z
dc.date.issued2015en_US
dc.description.abstractWe present a novel approach for making stereoscopic images by variational view synthesis on the multi-perspective light field. With the intended disparities as constraints, we specialize the generative variational model by incorporating per-pixel viewpoint assignment to synthesize the stereo pair. Also, we improve the variational solution by use of explicit weighted average on the light field. Our algorithm is able to handle arbitrary disparity remapping, thus enabling more flexible disparity control for the desired stereoscopic effect. The experiments demonstrate the effectiveness and efficiency for making the stereoscopic 3D images based on the light field.en_US
dc.description.number7en_US
dc.description.sectionheadersImage and Videoen_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume34en_US
dc.identifier.doi10.1111/cgf.12757en_US
dc.identifier.pages183-191en_US
dc.identifier.urihttps://doi.org/10.1111/cgf.12757en_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.titleEfficient Variational Light Field View Synthesis For Making Stereoscopic 3D Imagesen_US
Files
Collections