Author： Yuan Ze-Huan Lu Tong
Publisher： Springer Publishing Company
ISSN： 0924-669X
Source： Applied Intelligence, Vol.39, Iss.4, 2013-12, pp. : 761-771
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
We present a novel algorithm for 3D reconstruction in this paper, converting incremental 3D reconstruction to an optimization problem by combining two feature-enhancing geometric priors and one photometric consistency constraint under the Bayesian learning framework. Our method first reconstructs an initial 3D model by selecting uniformly distributed key images using a view sphere. Then once a new image is added, we search its correlated reconstructed patches and incrementally update the result model by optimizing the geometric and photometric energy terms. The experimental results illustrate our method is effective for incremental 3D reconstruction and can be further applied for large-scale datasets or to real-time reconstruction.
Related content
Model-Based 3D Object Recognition Using Bayesian Indexing
Computer Vision and Image Understanding, Vol. 69, Iss. 1, 1998-01 ,pp. :
Access to resources
Recommend
By Hisatomi Kensuke Katayama Miwa Tomiyama Kimihiro Iwadate Yuichi
International Journal of Computer Vision, Vol. 94, Iss. 1, 2011-08 ,pp. :