Integrated Frameworks for Three-dimensional Scene Reconstruction

Abstract

It has been shown in Chapters 1–3 that the problem of three-dimensional scene reconstruction can be addressed with a variety of approaches. Geometric approaches (cf. Chapter 1) rely on correspondences of points or higher-order features between several images of a scene acquired either with a moving camera or with several cameras from different viewpoints. These methods are accurate and do not require a-priori knowledge about the scene or the cameras used. On the contrary, as long as the scene points are suitably distributed they do not only yield the scene structure but also the intrinsic and extrinsic camera parameters, i.e. they perform a camera calibration simultaneously with the scene reconstruction. Geometric approaches, however, are restricted to parts of the scene with a sufficient amount of texture to decide which part of a certain image belongs to which part of another image. Occlusions may occur, such that corresponding points or features are hidden in some images, the appearance of the objects may change from image to image due to perspective distortions, and in the presence of objects with non-Lambertian surface properties the apparent intensity distribution across the scene may vary strongly from image to image, such that establishing correspondences between images becomes inaccurate or impossible at all.