@article {12060, title = {Visual space-time geometry - A tool for perception and the imagination}, journal = {Proceedings of the IEEE}, volume = {90}, year = {2002}, month = {2002/07//}, pages = {1113 - 1135}, abstract = {Although the fundamental ideas underlying research efforts in the field of computer vision have not radically changed in the past two decades, there has been a transformation in the way work in this field is conducted. This is primarily due to the emergence of a number of tools, of both a practical and a theoretical nature. One such tool, celebrated throughout the nineties, is the geometry of visual space-time. It is known under a variety of headings, such as multiple view geometry, structure from motion, and model building. It is a mathematical theory relating multiple views (images) of a scene taken at different viewpoints to three-dimensional models of the (possibly dynamic) scene. This mathematical theory gave rise to algorithms that take as input images (or video) and provide as output a model of the scene. Such algorithms are one of the biggest successes of the field and they have many applications in other disciplines, such as graphics (image-based rendering, motion capture) and robotics (navigation). One of the difficulties, however is that the current tools cannot yet be fully automated, and they do not provide very accurate results. More research is required for automation and high precision. During the past few years we have investigated a number of basic questions underlying the structure from motion problem. Our investigations resulted in a small number of principles that characterize the problem. These principles, which give rise to automatic procedures and point to new avenues for studying the next level of the structure from motion problem, are the subject of this paper.}, keywords = {3-D motion estimation, Buildings, Computer vision, Geometry, Graphics, Image sequences, Layout, Mathematical model, mathematical theory, model building, Motion estimation, multiple view geometry, multiple views, Navigation, optical flow, optical illusions, patch correspondence, Rendering (computer graphics), Robotics and automation, Solid modeling, structure from motion, three-dimensional models, visual space-time}, isbn = {0018-9219}, doi = {10.1109/JPROC.2002.801440}, author = {Ferm{\"u}ller, Cornelia and Baker, P. and Aloimonos, J.} }