Host: The Institute of Image Electronics Engineers of Japan
Co-host: Information Processing Society of Japan, Shinshu University
We propose an image-based rendering method called "layered probability mapping." The algorithm requires modest computer power, but produces high-quality output images even from textureless or noisy input images. Thus, real-time applications such as immersive teleconferencing and live broadcasting are promising areas of use. The key idea is layered probability map (LPM) representation using a set of two-dimensional probabilistic functions. This accommodates ambiguities regarding object depth.To test the feasibility of this method, we developed a prototype system with nine synchronized cameras and a thirteen-PC cluster. By calculating the algorithm in parallel, stable 7.5-fps image generation has been achieved without any off-line procedures between the image capture and display.