Automatic Multiperspective Images
dc.contributor.author | Román, Augusto | en_US |
dc.contributor.author | Lensch, Hendrik P. A. | en_US |
dc.contributor.editor | Tomas Akenine-Moeller and Wolfgang Heidrich | en_US |
dc.date.accessioned | 2014-01-27T14:55:28Z | |
dc.date.available | 2014-01-27T14:55:28Z | |
dc.date.issued | 2006 | en_US |
dc.description.abstract | Multiperspective 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.seriesinformation | Symposium on Rendering | en_US |
dc.identifier.isbn | 3-905673-35-5 | en_US |
dc.identifier.issn | 1727-3463 | en_US |
dc.identifier.uri | https://doi.org/10.2312/EGWR/EGSR06/083-092 | en_US |
dc.publisher | The Eurographics Association | en_US |
dc.subject | Categories 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 reality | en_US |
dc.title | Automatic Multiperspective Images | en_US |
Files
Original bundle
1 - 1 of 1