High-quality texture reconstruction from multiple scans

The creation of three-dimensional digital content by scanning real objects has become common practice in graphics applications for which visual qualit y is paramount, such as animation, e-commerce, and virtual museums. While a lot of attention has been devoted recently to the problem of accurately ca pturing the geometry of scanned objects, the acquisition of high-quality te xtures is equally important, but not as widely studied. In this paper, we f ocus on methods to construct accurate digital models of scanned objects by integrating high-quality texture and normal maps with geometric data. These methods are designed for use with inexpensive, electronic camera-based sys tems in which low-resolution range images and high-resolution intensity ima ges are acquired. The resulting models are well-suited for interactive rend ering on the latest-generation graphics hardware with support for bump mapp ing. Our contributions include new techniques for processing range, reflect ance, and surface normal data, for image-based registration of scans, and f or reconstructing high-quality textures for the output digital object.