Automatic Multiperspective Images

dc.contributor.authorRomán, Augustoen_US
dc.contributor.authorLensch, Hendrik P. A.en_US
dc.contributor.editorTomas Akenine-Moeller and Wolfgang Heidrichen_US
dc.date.accessioned2014-01-27T14:55:28Z
dc.date.available2014-01-27T14:55:28Z
dc.date.issued2006en_US
dc.description.abstractMultiperspective images generated from a collection of photographs or a videostream can be used to effectively summarize long, roughly planar scenes such as city streets. The final image will span a larger field of view than any single input image. However, common projections used to make these images, including cross-slits and pushbroom projections, may suffer from depth-related distortions in non-planar scenes. In this paper, we use an aspect-ratio distortion metric to compare these images to standard perspective projections. By minimizing this error metric we can automatically define the picture surface and viewpoints of a multiperspective image that reduces distortion artifacts. This optimization requires only a coarse estimate of scene geometry which can be provided as a depth map or a 2D spatial importance map defining interesting parts of the scene. These maps can be automatically constructed in most cases, allowing rapid generation of images of very long scenes.en_US
dc.description.seriesinformationSymposium on Renderingen_US
dc.identifier.isbn3-905673-35-5en_US
dc.identifier.issn1727-3463en_US
dc.identifier.urihttps://doi.org/10.2312/EGWR/EGSR06/083-092en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectCategories and Subject Descriptors (according to ACM CCS): I.3.3 [Picture/Image Generation]: Digitizing and scanning I.3.7 [Three-Dimensional Graphics and Realism]: Virtual realityen_US
dc.titleAutomatic Multiperspective Imagesen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
083-092.pdf
Size:
710.51 KB
Format:
Adobe Portable Document Format