Automatic registration of color images to 3D geometry of indoor environments

Abstract

In this thesis, we present an approach to automatically register a large set ofcolor images to a 3D geometric model. The problem arises from the modelingof real-world environments, where surface geometry is acquired using range scannerswhereas the color information is separately acquired using untracked andcalibrated cameras. Our approach constructs a sparse 3D model from the colorimages using a multiview geometry technique. The sparse model is then approximatelyaligned with the detailed model. We project special light patterns onto thescene surfaces to increase the robustness of the multiview-geometry reconstruction.Planes in the detailed model are exploited to re ne the registration. Finally, theregistered color images are mapped to the detailed model using weighted blending,with careful consideration of occlusion.