Eurographics Symposium on Rendering (2006) Tomas Akenine-Möller and Wolfgang Heidrich (Editors) Automatic Multiperspective Images

perspective varies continuously along this image, enabling an arbitrarily long seamless panorama. The perspective is automatically computed to minimize aspect ratio distortions in regions that have large depth variation such as road intersections. This figure is continued in high resolution on the bottom of each page throughout the paper. The image is not perfectly horizontal because the city itself has hills that are captured in the panorama. 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