TY - GEN
T1 - Dense multiple view stereo with general camera placement using tensor voting
AU - Mordohai, Philippos
AU - Medioni, Gérard
PY - 2004
Y1 - 2004
N2 - We present a computational framework for the inference of dense descriptions from multiple view stereo with general camera placement. Thus far research on dense multiple view stereo has evolved along three axes: computation of scene approximations in the form of visual hulls; merging of depth maps derived from simple configurations, such as binocular or trinocular; and multiple view stereo with restricted camera placement. These approaches are either sub-optimal, since they do not maximize the use of available information, or cannot be applied to general camera configurations. Our approach does not involve binocular processing other than the detection of tentative pixel correspondences. We require calibration information for all cameras and that there exist camera pairs which enable automatic pixel matching. The inference of scene surfaces is based on the premise that correct pixel correspondences, reconstructed in 3-D, form salient, coherent surfaces, while wrong correspondences form less coherent structures. The tensor voting framework is suitable for this task since it can process the very large datasets we generate with reasonable computational complexity. We show results on real images that present numerous challenges.
AB - We present a computational framework for the inference of dense descriptions from multiple view stereo with general camera placement. Thus far research on dense multiple view stereo has evolved along three axes: computation of scene approximations in the form of visual hulls; merging of depth maps derived from simple configurations, such as binocular or trinocular; and multiple view stereo with restricted camera placement. These approaches are either sub-optimal, since they do not maximize the use of available information, or cannot be applied to general camera configurations. Our approach does not involve binocular processing other than the detection of tentative pixel correspondences. We require calibration information for all cameras and that there exist camera pairs which enable automatic pixel matching. The inference of scene surfaces is based on the premise that correct pixel correspondences, reconstructed in 3-D, form salient, coherent surfaces, while wrong correspondences form less coherent structures. The tensor voting framework is suitable for this task since it can process the very large datasets we generate with reasonable computational complexity. We show results on real images that present numerous challenges.
UR - http://www.scopus.com/inward/record.url?scp=16244377761&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=16244377761&partnerID=8YFLogxK
U2 - 10.1109/TDPVT.2004.1335387
DO - 10.1109/TDPVT.2004.1335387
M3 - Conference contribution
AN - SCOPUS:16244377761
SN - 0769522238
SN - 9780769522234
T3 - Proceedings - 2nd International Symposium on 3D Data Processing, Visualization, and Transmission. 3DPVT 2004
SP - 725
EP - 732
BT - Proceedings - 2nd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2004
A2 - Aloimonos, Y.
A2 - Taubin, G.
T2 - Proceedings - 2nd International Symposium on 3D Data Processing, Visualization, and Transmission. 3DPVT 2004
Y2 - 6 September 2004 through 9 September 2004
ER -