tailieunhanh - Modeling the World from Internet Photo Collections

The availability of such rich imagery of large parts of the earth’s surface under many different viewing conditions presents enormous opportunities, both in computer vision research and for practical applications. From the standpoint of shape modeling research, Internet imagery presents the ultimate data set, which should enable modeling a significant portion of the world’s surface geometry at high resolution. As the largest, most diverse set of images ever assembled, Internet imagery provides deep insights into the space of natural images and a rich source of statistics and priors for modeling scene appearance. Furthermore, Internet imagery provides an ideal test bed for developing robust and general computer vision algorithms that can work effectively “in. | Int J Comput Vis DOI s11263-007-0107-3 Modeling the World from Internet Photo Collections Noah Snavely Steven M. Seitz Richard Szeliski Received 30 January 2007 Accepted 31 October 2007 Springer Science Business Media LLC 2007 Abstract There are billions of photographs on the Internet comprising the largest and most diverse photo collection ever assembled. How can computer vision researchers exploit this imagery This paper explores this question from the standpoint of 3D scene modeling and visualization. We present structure-from-motion and image-based rendering algorithms that operate on hundreds of images downloaded as a result of keyword-based image search queries like Notre Dame or Trevi Fountain. This approach which we call Photo Tourism has enabled reconstructions of numerous well-known world sites. This paper presents these algorithms and results as a first step towards 3D modeling of the world s well-photographed sites cities and landscapes from Internet imagery and discusses key open problems and challenges for the research community. Keywords Structure from motion 3D scene analysis Internet imagery Photo browsers 3D navigation 1 Introduction Most of the world s significant sites have been photographed under many different conditions both from the ground and from the air. For example a Google image search for Notre Dame returns over one million hits as of September 2007 showing the cathedral from almost every conceivable viewing position and angle different times of day and night and changes in season weather and decade. Furthermore entire cities are now being captured at street level and from a birds-eye perspective . Windows Live Local 1 2 and Google Streetview1 2 3 and from satellite or aerial views . Google4 . The availability of such rich imagery of large parts of the earth s surface under many different viewing conditions presents enormous opportunities both in computer vision research and for practical applications. From the standpoint