DocumentCode :
579859
Title :
Least Commitment, Viewpoint-Based, Multi-view Stereo
Author :
Hu, Xiaoyan ; Mordohai, Philippos
Author_Institution :
Stevens Inst. of Technol., Hoboken, NJ, USA
fYear :
2012
fDate :
13-15 Oct. 2012
Firstpage :
531
Lastpage :
538
Abstract :
We address the problem of large-scale 3D reconstruction from calibrated images relying on a viewpoint-based approach. The representation is in the form of a collection of depth maps, which are fused to blend consistent depth estimates and minimize violations of visibility constraints. We adopt a least commitment strategy by allowing multiple candidate depth values per pixel in the fusion process and deferring hard decisions as much as possible. To address the inevitable noise in the depth maps, we explicitly model its sources, namely mismatches and inaccurate 3D coordinate estimation via triangulation, by measuring two types of uncertainty and using the uncertainty estimates to guide the fusion process. To the best of our knowledge, this is the first attempt to model both geometric and correspondence uncertainty in the context of dense 3D reconstruction. We show quantitative results on datasets with ground truth that are competitive with the state of the art.
Keywords :
calibration; image reconstruction; stereo image processing; calibrated images; depth estimates; depth maps; inaccurate 3D coordinate estimation; large-scale 3D reconstruction; least commitment stereo; multi-view stereo; multiple candidate depth values; viewpoint-based stereo; Cameras; Estimation; Image reconstruction; Solid modeling; Surface reconstruction; Three dimensional displays; Uncertainty; 3D reconstruction; depth map fusion; stereo vision;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), 2012 Second International Conference on
Conference_Location :
Zurich
Print_ISBN :
978-1-4673-4470-8
Type :
conf
DOI :
10.1109/3DIMPVT.2012.60
Filename :
6375038
Link To Document :
بازگشت