We present a system for producing multi-viewpoint panoramas of long, roughly planar scenes, such as the facades of buildings along a city street, from a relatively sparse set of photographs captured with a handheld still camera that is moved along the scene. Our work is a significant departure from previous methods for creating multi-viewpoint panoramas, which composite thin vertical strips from a video sequence captured by a translating video camera, in that the resulting panoramas are composed of relatively large regions of ordinary perspective. In our system, the only user input required beyond capturing the photographs themselves is to identify the dominant plane of the photographed scene; our system then computes a panorama automatically using Markov Random Field optimization. Users may exert additional control over the appearance of the result by drawing rough strokes that indicate various high-level goals. We demonstrate the results of our system on several scenes, including urban streets, a river bank, and a grocery store aisle.
Aseem Agarwala, Maneesh Agrawala, Michael Cohen, David Salesin, Richard Szeliski. Photographing long scenes with multi-viewpoint panoramas. ACM Transactions on Graphics (Proceedings of SIGGRAPH 2006), 2006.
SIGGRAPH 2006 pre-print (4MB PDF)
For each result we show a movie clip of the source images and a thumbnail image that links to the full resolution result. When you view the full resolution image, your browser will likely scale it (poorly) to the width of the window. In Firefox, clicking on the scaled image will show it un-scaled. In Internet Explorer, hovering the mouse over the scaled image should give you a button in the lower-right to un-scale the image.
|Input photographs (video)||Multi-viewpoint panorama|