TY - GEN
T1 - PatchMatch based joint view selection and depthmap estimation
AU - Zheng, Enliang
AU - Dunn, Enrique
AU - Jojic, Vladimir
AU - Frahm, Jan Michael
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/9/24
Y1 - 2014/9/24
N2 - We propose a multi-view depthmap estimation approach aimed at adaptively ascertaining the pixel level data associations between a reference image and all the elements of a source image set. Namely, we address the question, what aggregation subset of the source image set should we use to estimate the depth of a particular pixel in the reference image? We pose the problem within a probabilistic framework that jointly models pixel-level view selection and depthmap estimation given the local pairwise image photoconsistency. The corresponding graphical model is solved by EM-based view selection probability inference and PatchMatch-like depth sampling and propagation. Experimental results on standard multi-view benchmarks convey the state-of-the art estimation accuracy afforded by mitigating spurious pixel level data associations. Additionally, experiments on large Internet crowd sourced data demonstrate the robustness of our approach against unstructured and heterogeneous image capture characteristics. Moreover, the linear computational and storage requirements of our formulation, as well as its inherent parallelism, enables an efficient and scalable GPU-based implementation.
AB - We propose a multi-view depthmap estimation approach aimed at adaptively ascertaining the pixel level data associations between a reference image and all the elements of a source image set. Namely, we address the question, what aggregation subset of the source image set should we use to estimate the depth of a particular pixel in the reference image? We pose the problem within a probabilistic framework that jointly models pixel-level view selection and depthmap estimation given the local pairwise image photoconsistency. The corresponding graphical model is solved by EM-based view selection probability inference and PatchMatch-like depth sampling and propagation. Experimental results on standard multi-view benchmarks convey the state-of-the art estimation accuracy afforded by mitigating spurious pixel level data associations. Additionally, experiments on large Internet crowd sourced data demonstrate the robustness of our approach against unstructured and heterogeneous image capture characteristics. Moreover, the linear computational and storage requirements of our formulation, as well as its inherent parallelism, enables an efficient and scalable GPU-based implementation.
UR - http://www.scopus.com/inward/record.url?scp=84911455570&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84911455570&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2014.196
DO - 10.1109/CVPR.2014.196
M3 - Conference contribution
AN - SCOPUS:84911455570
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1510
EP - 1517
BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Y2 - 23 June 2014 through 28 June 2014
ER -