Microsoft Photosynth
Photosynth is a software application from Microsoft Live Labs and the University of Washington that analyzes digital photographs and generates a three-dimensional model of the photos and a point cloud of a photographed object.[1] Pattern recognition components compare portions of images to create points, which are then compared to convert the image into a model. Users are able to view and generate their own models using a software tool available for download at the Photosynth website.
Photosynth is based on Photo Tourism, a research project by University of Washington graduate student Noah Snavely.[2]
Microsoft released a free tech preview version on November 9, 2006. Users could view models generated by Microsoft or the BBC, but not create their own models at that time.[3] Microsoft teamed up with NASA on August 6, 2007 allowing users to preview its Photosynth technology showing the Space Shuttle Endeavour. On August 20, 2007, a preview showing the tiles of Endeavour during the backflip process was made available for viewing.
On August 20, 2008, Microsoft officially released Photosynth to the public, allowing users to upload their images and generate their own Photosynth models.
The Photosynth technology works in two steps. The first step involves the analysis of multiple photographs taken of the same area. Each photograph is processed using an interest point detection and matching algorithm developed by Microsoft Research which is similar in function to UBC‘s Scale-invariant feature transform. This process identifies specific features, for example the corner of a window frame or a door handle. Features in one photograph are then compared to and matched with the same features in the other photographs. Thus photographs of the same areas are identified. By analyzing the position of matching features within each photograph, the program can identify which photographs belong on which side of others. By analyzing subtle differences in the relationships between the features (angle, distance, etc.), the program identifies the 3D position of each feature, as well as the position and angle at which each photograph was taken. This process is known scientifically as Bundle adjustment and is commonly used in the field of photogrammetry, with similar products available such as Imodeller, D-Sculptor, and Rhinoceros. This first step is extremely computationally intensive, but only has to be performed once on each set of photographs.
The second step involves the display of and navigation through the 3D point cloud of features identified in the first step. This is done with the publicly downloadable Photosynth viewer. The viewer resides on a client computer and maintains a connection to a server that stores the original photographs. It enables a user to, among other things, see any of the photographs from their original vantage point. It incorporates DeepZoom technology Microsoft obtained through its acquisition of Seadragon in January 2006. The Seadragon technology enables smooth zooming into the high-resolution photographs without downloading them to the user’s machine.
mrlee1989
