Thursday, August 10, 2006

3D Photo Tourism Project Showcased at SIGGRAPH


Several months ago I was contacted by researchers working on an immersive 3D Photo Tourism project at the Computer Science Department at the University of Washington.

"A central goal of image-based rendering is to evoke a visceral sense of presence based on a collection of photographs of a scene. The last several years have seen signicant progress towards this goal through view synthesis methods in the research community and in commercial products such as panorama tools. One of the dreams
is that these approaches will one day allow virtual tourism of the world's interesting and important sites.

During this same time, digital photography, together with the Internet, have combined to enable sharing of photographs on a truly massive scale. For example, a Google image search on “Notre Dame Cathedral” returns over 15,000 photos, capturing the scene from myriad viewpoints, levels of detail, lighting conditions, seasons, decades, and so forth. Unfortunately, the proliferation of shared photographs has outpaced the technology for browsing such
collections, as tools like Google (www.google.com) and Flickr (www.ickr.com) return pages and pages of thumbnails that the user must comb through.

We present a system for browsing and organizing large photo collections of popular sites which exploits the common 3D geometry of the underlying scene. Our approach is based on
computing, from the images themselves, the photographers' locations and orientations, along with a sparse 3D geometric representation of the scene, using a state-of-the-art image-based modeling system. Our system handles large collections of unorganized photographs
taken by different cameras in widely different conditions.

We show how the inferred camera and scene information enables the following capabilities:

Scene visualization. Fly around popular world sites in 3D by morphing between photos.

Object-based photo browsing. Show me more images that contain this object or part of the scene.

Where was I? Tell me where I was when I took this picture.

What am I looking at? Tell me about objects visible in this image by transferring annotations from similar images." - Photo Tourism: Exploring Photo Collections in 3D

The researchers requested permission to use some of my pictures of Trevi Fountain for a demonstration of their new system for creating an interactive environment for visual exploration of historical sites that have been photographed from many different angles at various times of the year by many different people. The demonstration was presented at Siggraph. You can view the system at:

http://phototour.cs.washington.edu/

I recommend watching the longer movie which explains the interactive features more in depth. I found it to be a fascinating learning environment and feel honored to have had some of my images selected for inclusion in such a cutting edge project. It really motivates me to continue to build my online archive for educational use.

No comments: