Georgios Vouzounaras
ABSTRACT
In this paper, a novel method is proposed able to automatically generate accurate 3D models of both outdoor buildings and indoor scenes with perspective cues from line segments that are automatically extracted from a single image with an uncalibrated camera. The proposed method uses geometric constraints and knowledge of photography and achieves an accurate, real-time and fully automated 3D reconstruction of the scene without any intervention from the user.
- J. M. Coughlan and A. L. Yuille. Manhattan world: Compass direction from a single image by Bayesian inference. In ICCV '99: Proceedings of the International Conference on Computer Vision- Volume 2, page 941, Washington, DC, USA, 1999. IEEE Computer Society. DOI= http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.5078 . Google Scholar
Digital Library
- A. Criminisi, I. Reid, and A. Zisserman. Single view metrology. Int. J. Computer Vision, 40(2):123--148, 2000. DOI= http://portal.acm.org/citation.cfm?id=365888 . Google ScholarDigital Library
- A. Criminisi, I. Reid, and A. Zisserman. A plane measuring device. Image and Vision Computing, 17(8):625--634, 1999.Google ScholarCross Ref
- E. Delage, H. Lee, and A. Y. Ng. A dynamic Bayesian network model for autonomous 3d reconstruction from a single indoor image. Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, 2:2418--2428, 2006. DOI= http://www.stanford.edu/~hllee/cvpr06_3dReconIndoorScene.pdf Google ScholarDigital Library
- Google Sketch Up. http://sketchup.google.com/Google Scholar
- R. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, 2003. Google ScholarDigital Library
- D. Hoiem, A. Efors, and M. Hebert. Geometric context from a single image. In Proceedings of IEEE Conference Computer Vision and Pattern Recognition, 2005. DOI = http://www.cs.uiuc.edu/homes/dhoiem/publications/Hoiem_Geometric.pdfGoogle ScholarDigital Library
- J. Huang and B. Cowan. Simple 3D Reconstruction of Single Indoor Image with Perspective Cues. crv, pp.140--147, 2009 Canadian Conference on Computer and Robot Vision. DOI= http://www.computer.org/portal/web/csdl/doi/10.1109/CRV.2009.33 Google ScholarDigital Library
- D. C. Lee, M. Hebert and T. Kanade. Geometric Reasoning for Single Image Structure Recovery. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June, 2009. DOI= www.cs.cmu.edu/~dclee/pub/cvpr09lee.pdfGoogle Scholar
- D. Liebowitz, Antonio Criminisi, and Andrew Zisserman. 1999. Creating Architectural Models from Images. In Proc. EuroGraphics, vol.18, 1999. DOI= http://www.robots.ox.ac.uk/~vgg/publications/papers/liebowitz99.pdf .Google ScholarCross Ref
- D. Liebowitz, Camera Calibration and Reconstruction of Geometry from Images. Merton College Robotics Research Group Department of Engineering Science University of Oxford Trinity Term 2001. DOI= http://www.robots.ox.ac.uk/~vgg/publications/papers/liebowitz01.pdfGoogle Scholar
- C. Rother. A new approach for vanishing point detection in architectural environments. In BMVC, pages 382--391, 2000. DOI= www.bmva.org/bmvc/2000/papers/p39.pdfGoogle Scholar
- A. Saxena, S. H. Chung, and A. Y. Ng. Learning depth from single monocular images. In Neural Information Processing Systems (NIPS), 2005. DOI = http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.8799Google Scholar
Index Terms
- 3D reconstruction of indoor and outdoor building scenes from a single image
Recommendations
Automatic generation of 3D outdoor and indoor building scenes from a single image
In this paper, a novel approach for creating 3D models of building scenes is presented. The proposed method is fully automated and fast, and accurately reconstructs both outdoor images of a building and indoor scenes, with perspective cues in real-time, ...
Traffic surveillance camera calibration by 3D model bounding box alignment for accurate vehicle speed measurement
Improved traffic camera calibration method based on vanishing points detection.Automatic scene scale inference by alignment of 3D model bounding box.Extensive experiments on a recent speed measurement dataset BrnoCompSpeed.Results show that our method ...
3D Reconstruction of Indoor Scenes via Image Registration
With the development of computer vision technologies, 3D reconstruction has become a hotspot. At present, 3D reconstruction relies heavily on expensive equipment and has poor real-time performance. In this paper, we aim at solving the problem of 3D ...
Comments