Visual 3D modeling of real-world objects and scenes from images
Google Tech Talks
May 1, 2007
Images and videos form a rich source of information about the visual world. The extraction of 3D information from images is an important research problem in computer vision and graphics. The ubiquitous presence of cameras and the tremendous advances of processing and communication technologies yields important opportunities and challenges in those areas.
My work has focused on developing flexible techniques for recovering 3D shape, motion and appearance from images. A first example of this is an approach to recover photo-realistic 3D models of static objects or scenes from videos recorded with a hand-held camera or on a moving vehicle. A key aspect of our approach is the ability to also recover the geometric and photometric calibration of the camera from the image data so that our techniques can also work with uncalibrated consumer cameras or archive photographs. Towards the end of my talk, I will also briefly discuss approaches to capture dynamic scenes, both from single and multiple cameras. Applications ranging from archaeology and 3D urban modeling, to special effects and 3D tele-medecine will be used to illustrate our work.