TY - GEN
T1 - A generative model for online depth fusion
AU - Woodford, Oliver J.
AU - Vogiatzis, George
PY - 2012
Y1 - 2012
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84867849466&partnerID=8YFLogxK
UR - http://link.springer.com/chapter/10.1007%2F978-3-642-33715-4_11
U2 - 10.1007/978-3-642-33715-4_11
DO - 10.1007/978-3-642-33715-4_11
M3 - Conference publication
AN - SCOPUS:84867849466
SN - 978-3-642-33714-7
T3 - Lecture notes in computer science
SP - 144
EP - 157
BT - Computer vision – ECCV 2012
A2 - Fitzgibbon, Andrew
A2 - Lazebnik, Svetlana
A2 - Perona, Pietro
A2 - Sato, Yoichi
A2 - Schmid, Cordelia
PB - Springer
CY - Berlin (DE)
T2 - 12th European Conference on Computer Vision
Y2 - 7 October 2012 through 13 October 2012
ER -