A 3D Pseudo-Reconstruction from Single ImageBased on Vanishing Point
Jingjing Wang*, Fangyan Dong*, Takashi Takegami**, Eiroku Go**, and Kaoru Hirota*
*Dept. of Computational Intelligence and Systems Science, Tokyo Institute of Technology, G3-49, 4259 Nagatsuta, Midori-ku, Yokohama-city 226-8502, Japan
**Customer Solutions Development Co., Ltd., 6F, West Wing, KSP BLDG, 3-2-1 Sakado, Takatsu-ku, Kawasaki-city, 213-0012, Japan
A 3D (three-dimensional) pseudo-reconstruction method from a single image is presented as a novel approach reconstructing a 3D model with no prior internal knowledge of outdoors image. In the proposed method, an image is represented as a collection of sky layer, ground layer, and object layer. A visual radical coordinate system with vanishing point is established to accommodate the extracted 3D data from images. Learning method is done via the layers database. The experiment results show that the visually acceptable 3D model can be extracted less than one minute. That means a higher resolution in much shorter time, compared to conventional methods. This method can be applied to computer games, industrial measurement, archeology, architecture and visual realities.
-  N. K. Kutulako and S. M. Seitz, “A theory of shape by space carving,” in Proc. IJCV, pp. 199-218, 2000.
-  F. Dellaert, S. Seitz, C. Thorpe, and S. Thrun, “Structure from Motion without Correspondence,” in Proc. CVPR, Vol.2, pp. 557-564, 2000.
-  M. Pollefeys, R. Koch, and L. Van Gool, “Self calibration and metric reconstruction in spite of varying and unknown internal camera parameters,” in Proc. ICCV, pp. 90-95, 1998.
-  A. R. Dick, P. H. S. Torr, and R. Cipolla, “A bayesian estimation of building shape using MCMC,” in Proc. ECCV, pp. 852-866, 2002.
-  H. Schneiderman, “Learning a restricted Bayesian network for object detection,” in Proc. CVPR, Vol.2, pp. 639-646, 2004.
-  F. Han and S. C. Zhu, “Bayesian reconstruction of 3d shapes and scenes from a single image,” in Int. Work. On Higher-Level Know, in 3D Modeling and Motion Anal, pp. 12-20, 2003.
-  S. Kumar and M. Hebert, “Discriminative random fields: A discriminative framework for contextual interaction in classification,” in Proc. ICCV, Vol.2, pp. 1150-1157, 2003.
-  P. F. Felzenszwalb and D. P. Huttenlocher, “Efficient graph-based image segmentation,” Int. Journal of Computer Vision, Vol.59, No.2, pp. 167-181, 2004.
-  D. Hoiem, A. A. Efros, and M. Hebert, “Automatic photo popup,” in ACM SIGGRAPH, pp. 577-584, 2005.
-  B. Bose and W. E. L. Grimson, “Improving object classification n far-field video,” in Proc. CVPR, Vol.2, pp. 181-188, 2004.
-  A. Torralba, K. P. Murphy, and W. T. Freeman, “Contextual models for object detection using boosted random fields,” in Proc. NIPS, 2004.
-  D. Hoiem, A. N. Stein, A. A. Efros, and M. Hebert, “Recovering Occlusion Boundaries from a Single Image,” ICCV, 2007.
-  Y. Shan, F. Han, H. S. Sawhney, and R. Kumar, “Learning Exemplar-based Categorization for the Detection of Multi-view Multi-pose Objects,” In Proc. CVPR, Vol.2, pp. 1431-1438, 2006.
-  S. M. Seitz, B. Curless, J. Diebel, D. Scharstein, and R. Szeliski, “A comparison and evaluation of multi-view stereo reconstruction algorithms,” In Proc. CVPR, pp. 519-528, 2006.
-  N. Snavely, S. M. Seitz, and R. Szeliski, “Photo tourism: exploring photo collections in 3D,” In SIGGRPH Conf. Proc., pp. 835-846, 2006.