Reconstructing the World's Museums
Venue
European Conference on Computer Vision (2012) (to appear)
Publication Year
2012
Authors
Jianxiong Xiao, Yasutaka Furukawa
BibTeX
Abstract
Photorealistic maps are a useful navigational guide for large indoor environments,
such as museums and businesses. However, it is impossible to acquire photographs
covering a large indoor environment from aerial viewpoints. This paper presents a
3D reconstruction and visualization system to automatically produce clean and
well-regularized texture-mapped 3D models for large indoor scenes, from
ground-level photographs and 3D laser points. The key component is a new algorithm
called "Inverse CSG" for reconstructing a scene in a Constructive Solid Geometry
(CSG) representation consisting of volumetric primitives, which imposes powerful
regularization constraints to exploit structural regularities. We also propose
several techniques to adjust the 3D model to make it suitable for rendering the 3D
maps from aerial viewpoints. The visualization system enables users to easily
browse a large scale indoor environment from a bird's-eye view, locate specific
room interiors, fly into a place of interest, view immersive ground-level panorama
views, and zoom out again, all with seamless 3D transitions. We demonstrate our
system on various museums, including the Metropolitan Museum of Art in New York
City -- one of the largest art galleries in the world.
