Issue No. 02 - March/April (2002 vol. 22)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/38.988748
<p>In research on 3D image communications and virtual reality, the development of techniques for synthesizing arbitrary views has become an important technical issue. Given a structural model (such as a polygon or volume model) of an object, it is relatively easy to synthesize arbitrary views. Generating a structural model of an object, however, is not necessarily easy. For this reason, research has been progressing on a technique called image-based modeling and rendering (IBMR) as a means of avoiding this problem. To date, studies have been performed on a variety of specific IBMR techniques. In this article, we target 3D scenes in motion and describe a system that can perform processing in real time from image pickup to interactive display. We call the system a video-based rendering (VBR) system, since it utilizes video sequences instead of static images. The experimental results reported here show that our method is useful for interactive 3-D rendering of real scenes.</p>
light field, camera array, layered representation, Image-Based Modeling and Rendering, Video-Based Rendering
T. Naemura, H. Harashima and J. Tago, "Real-Time Video-Based Modeling and Rendering of 3D Scenes," in IEEE Computer Graphics and Applications, vol. 22, no. , pp. 66-73, 2002.