scale Image-based Modeling · 3D Reconstruction

Abstract Virtual exploration tools for large indoor environ-ments (e.g. museums) have so far been limited to either blueprint-style 2D maps that lack photo-realistic views of scenes, or ground-level image-to-image transitions, which are immer-sive but ill-suited for navigation. On the other hand, photo-realistic aerial maps would be a useful navigational guide for large indoor environments, but it is impossible to di-rectly acquire photographs covering a large indoor environ-ment from aerial viewpoints. This paper presents a 3D re-construction and visualization system for automatically pro-ducing clean and well-regularized texture-mapped 3D mod-els 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 with a Con-structive Solid Geometry (CSG) representation consisting of volumetric primitives, which imposes powerful regulariza-tion constraints. We also propose several novel techniques to adjust the 3D model to make it suitable for rendering the 3D maps from aerial viewpoints. The visualization sys-tem enables users to easily browse a large-scale indoor en-vironment from a bird’s-eye view, locate specific room in-teriors, 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 mu-seums, including the Metropolitan Museum of Art in New York City – one of the largest art galleries in the world