TY - GEN
T1 - Simplified belief propagation for multiple view reconstruction
AU - Larsen, E. Scott
AU - Mordohai, Philippos
AU - Pollefeys, Marc
AU - Fuchs, Henry
PY - 2006
Y1 - 2006
N2 - We address multiple-view reconstruction under an optimization approach based on belief propagation. A novel formulation of belief propagation that operates in 3-D is proposed to facilitate a true multi-image processing scheme that takes visibility into account and thus is applicable to scenes that contain significant occlusions. Visibility is not approximated but is estimated and used in a modified plane sweep stereo scheme. Optimization is performed in a simplified belief propagation framework in which messages are passed in 3-D, instead of 2-D, neighborhoods utilizing information from all available images. The information propagated from a point to one of its neighbors factors in the distance between the two points in 3-D, their difference in color. In contrast to traditional belief propagation, the observation is updated at each iteration to incorporate changes in visibility. The proposed approach is capable of enforcing smoothness on the evolving 3-D surfaces without being limited to a coarse resolution due to a volumetric representation. Moreover, our approach is applicable to both open and closed surfaces with no need for a priori knowledge of the type. We present dense reconstructions of publicly available image sets.
AB - We address multiple-view reconstruction under an optimization approach based on belief propagation. A novel formulation of belief propagation that operates in 3-D is proposed to facilitate a true multi-image processing scheme that takes visibility into account and thus is applicable to scenes that contain significant occlusions. Visibility is not approximated but is estimated and used in a modified plane sweep stereo scheme. Optimization is performed in a simplified belief propagation framework in which messages are passed in 3-D, instead of 2-D, neighborhoods utilizing information from all available images. The information propagated from a point to one of its neighbors factors in the distance between the two points in 3-D, their difference in color. In contrast to traditional belief propagation, the observation is updated at each iteration to incorporate changes in visibility. The proposed approach is capable of enforcing smoothness on the evolving 3-D surfaces without being limited to a coarse resolution due to a volumetric representation. Moreover, our approach is applicable to both open and closed surfaces with no need for a priori knowledge of the type. We present dense reconstructions of publicly available image sets.
UR - http://www.scopus.com/inward/record.url?scp=47249094149&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=47249094149&partnerID=8YFLogxK
U2 - 10.1109/3DPVT.2006.129
DO - 10.1109/3DPVT.2006.129
M3 - Conference contribution
AN - SCOPUS:47249094149
SN - 0769528252
SN - 9780769528250
T3 - Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
SP - 342
EP - 349
BT - Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
T2 - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
Y2 - 14 June 2006 through 16 June 2006
ER -