Range image registration based on photometry 光学解析に基づく距離画像の位置合わせ

博士論文

3D modeling of a real scene stands for constructing a virtual representation of the scene, generally simplified that can be used or modified at our will. Constructing such a 3D model by hand is a laborious and time consuming task, and automating the whole process has attracted growing interest in the computer vision field. In particular, the task of registering (i.e. aligning) different parts of the scene (called range images) acquired from different viewpoints is of crucial importance when constructing 3D models. During the last decades, researchers have concentrated their efforts on this problem and proposed several methodologies to automatically register range images. Thereby, key-point detectors and descriptors have been utilized to match points across different range images using geometric features or textural features. Several similarity metrics have also been proposed to identify the overlapping regions. In spite of the advantages of the current methods, several limitation cases have been reported. In particular, when the scene lacks in discriminative geometric features, the difficulty of accounting for the changes in appearance of the scene observed in different poses, or from different viewpoints, significantly degrades the performance of the current methods. We address this issue by investigating the use of photometry (i.e. the relationship between geometry, reflectance properties and illumination) for range image registration. First, we propose a robust descriptor using albedo that is permissive to errors in the illumination estimation. Second, we propose an albedo extraction technique for specular surfaces that enlarges the range of materials we can deal with. Third, we propose a photometric metric under unknown lighting that allows registration of range images without any assumptions on the illumination. With these proposed methods, we significantly enlarge the practicability and range of applications of range image registration.

総研大甲第1517号