Title :
Real-time video-based modeling and rendering of 3D scenes
Author :
Naemura, Takeshi ; Tago, Junji ; Harashima, Hiroshi
Author_Institution :
Stanford Univ., CA, USA
Abstract :
Our work targets 3D scenes in motion. In this article, we propose a method for view-dependent layered representation of 3D dynamic scenes. Using densely arranged cameras, we´ve developed a system that can perform processing in real time from image pickup to interactive display, using video sequences instead of static images, at 10 frames per second. In our system, images on layers are view dependent, and we update both the shape and image of each layer in real time. This lets us use the dynamic layers as the coarse structure of the dynamic 3D scenes, which improves the quality of the synthesized images. In this sense, our prototype system may be one of the first full real-time image -based modelling and rendering systems. Our experimental results show that this method is useful for interactive 3D rendering of real scenes
Keywords :
image sequences; real-time systems; rendering (computer graphics); stereo image processing; video signal processing; 3D dynamic scenes; coarse structure; densely arranged cameras; image pickup; interactive 3D rendering; interactive display; real-time video-based modeling; real-time video-based rendering; video sequences; view-dependent layered representation; Cameras; Character generation; Computer graphics; Image sensors; Intelligent sensors; Layout; Rendering (computer graphics); Sensor arrays; Three dimensional displays; Video sequences;
Journal_Title :
Computer Graphics and Applications, IEEE