Abstract | ||
---|---|---|
3D reconstruction with missing data has been a very challenging computer vision task since the late 90s. This paper proposes the GPU-powered version of our weak-perspective Structure from Motion algorithm published in BMVC2008. Although this method is iterative, it is very rapid since all substeps in each iteration minimize the parameters optimally with respect to the reprojection error. We demonstrate here in both synthetic and real tests that the use of the GPU significantly reduces the time demand of the algorithm. Real-time 3D reconstruction is possible if the parameters of the optimization algorithm are set properly. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICCVW.2011.6130283 | Computer Vision Workshops |
Keywords | Field | DocType |
computer vision,graphics processing units,image reconstruction,minimisation,parameter estimation,solid modelling,BMVC2008,GPU-powered version,computer vision,missing data,motion algorithm,optimization algorithm,parameter minimization,real-time 3D reconstruction,reprojection error,weak-perspective structure | Iterative reconstruction,Structure from motion,Approximation algorithm,Computer vision,Reprojection error,Computer science,Minimisation (psychology),Artificial intelligence,Estimation theory,Missing data,3D reconstruction | Conference |
ISBN | Citations | PageRank |
978-1-4673-0062-9 | 0 | 0.34 |
References | Authors | |
14 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Csaba Kazó | 1 | 0 | 0.34 |
Levente Hajder | 2 | 43 | 12.55 |