TY - GEN
T1 - An extension of PatchMatch Stereo for 3D reconstruction from multi-view images
AU - Hiradate, Mutsuki
AU - Ito, Koichi
AU - Aoki, Takafumi
AU - Watanabe, Takafumi
AU - Unten, Hiroki
PY - 2016/6/7
Y1 - 2016/6/7
N2 - PatchMatch Stereo is a method generating a depth map from stereo images by repeatedly applying spatial propagation and view propagation to the depth map. The extension of PatchMatch Stereo for multi-view 3D reconstruction has been recently proposed. This extension is very ad hoc and does not fully utilize the potential of multi-view images, since the method generates a 3D point cloud by combining a set of depth maps obtained from each binocular stereo image pair. This paper proposes a multi-view 3D reconstruction method using PatchMatch Stereo. To fully utilize the impact of multi-view images, the proposed method have two key ideas: (i) integrate matching scores from multiple stereo image pairs and (ii) perform view propagation among multi-view images. The use of multi-view images makes it possible to generate a reliable depth map by reducing occlusions. Through a set of experiments, we demonstrate that the proposed method generates more reliable depth map from multi-view images than the conventional method.
AB - PatchMatch Stereo is a method generating a depth map from stereo images by repeatedly applying spatial propagation and view propagation to the depth map. The extension of PatchMatch Stereo for multi-view 3D reconstruction has been recently proposed. This extension is very ad hoc and does not fully utilize the potential of multi-view images, since the method generates a 3D point cloud by combining a set of depth maps obtained from each binocular stereo image pair. This paper proposes a multi-view 3D reconstruction method using PatchMatch Stereo. To fully utilize the impact of multi-view images, the proposed method have two key ideas: (i) integrate matching scores from multiple stereo image pairs and (ii) perform view propagation among multi-view images. The use of multi-view images makes it possible to generate a reliable depth map by reducing occlusions. Through a set of experiments, we demonstrate that the proposed method generates more reliable depth map from multi-view images than the conventional method.
UR - http://www.scopus.com/inward/record.url?scp=84978887435&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84978887435&partnerID=8YFLogxK
U2 - 10.1109/ACPR.2015.7486466
DO - 10.1109/ACPR.2015.7486466
M3 - Conference contribution
AN - SCOPUS:84978887435
T3 - Proceedings - 3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015
SP - 61
EP - 65
BT - Proceedings - 3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015
Y2 - 3 November 2016 through 6 November 2016
ER -