With the recent rise in popularity of Internet photo sharing sites like Flickr and Google Images, community photo collections (CPCs) have emerged as a powerful new type of image dataset for computer vision and computer graphics research. With billions of such photos now online, these collections should enable huge opportunities in 3D, visualization, image-based rendering, recognition, and other research areas. The Graphics and Imaging Laboratory of the University of Washington‘s Department of Computer Science and Engineering are at the cutting edge of research based around crowd sourced imagery and 3D modelling.
In their project ‘Bulding Rome in a Day’ the group considered the problem of reconstructing entire cities from images harvested from the web. The aim is to build a parallel distributed system that downloads all the images associated with a city from Flickr.com. After downloading, it matches these images to find common points and uses this information to compute the three dimensional structure of the city and the pose of the cameras that captured these images. All this to be done in a day.
The movie below details thier sample work using 58,000 images of Dubrovnik sourced from Flickr:
If you do anything today check out their Building Rome in a Day page for further movies and details.
So whats the difference between this and microsofts photosynth?
@Ankit Photo Tourism (the predecessor to this work) is a research publication in SIGGRAPH. Microsoft Photosynth is an industry implementation. Check out this article: