 |
    |
A Generative Model for Online Depth Fusion
Oliver J. Woodford1 and George Vogiatzis2
1Toshiba Research Europe Ltd., Cambridge, UK
2Aston University, Birmingham, UK
Abstract. We present a probabilistic, online, depth map fusion framework, whose generative model for the sensor measurement process accurately incorporates both long-range visibility constraints and a spatially varying, probabilistic outlier model. In addition, we propose an inference algorithm that updates the state variables of this model in linear time each frame. Our detailed evaluation compares our approach against several others, demonstrating and explaining the improvements that this model offers, as well as highlighting a problem with all current methods: systemic bias.
LNCS 7576, p. 144 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012