Shape from regularities for interactive 3D reconstruction of piecewise planar objects from single images

ABSTRACT

3D object reconstruction from single 2D images has many applications in multimedia. This paper proposes an approach based on image regularities such as connectivity, parallelism, and orthogonality possessed by the objects with simple user interactions. It is assumed that the objects are piecewise planar. By representing the 3D objects as a shape vector consisting of the normals of the faces of the objects, we impose geometric constraints on this shape vector using the regularities of the objects. We derive a system of equations in terms of the shape vector and the focal length, which we can solve for the shape vector optimally. Experimental results on real images are shown to demonstrate the effectiveness of this method.

REFERENCES

• 1: Richard Hartley , Andrew Zisserman, Multiple view geometry in computer visiond, Cambridge University Press, New York, NY, 2001
• 2: David Jelinek , Camillo J. Taylor, Reconstruction of Linearly Parameterized Models from Single Images with a Camera of Unknown Focal Length, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.23 n.7, p.767-773, July 2001 [doi>10.1109/34.935850 ]
• 3: Paul E. Debevec , Camillo J. Taylor , Jitendra Malik, Modeling and rendering architecture from photographs: a hybrid geometry- and image-based approach, Proceedings of the 23rd annual conference on Computer graphics and interactive techniques, p.11-20, August 1996 [doi>10.1145/237170.237191]
• 4: D. Liebowitz, A. Criminisi, and A. Zisserman. Creating architectural models from images. Proc. EuroGraphics, vol. 18, pp. 39--50, Sept. 1999.
• 5: Liangliang Cao , Jianzhuang Liu , Xiaoou Tang, 3D object retrieval using 2D line drawing and graph based relevance reedback, Proceedings of the 14th annual ACM international conference on Multimedia, October 23-27, 2006, Santa Barbara, CA, USA [doi>10.1145/1180639.1180671]
• 6: M. Prasad, A. Zisserman, and A. W. Fitzgibbon. Fast and controllable 3D modelling from silhouettes. Proc. of the 26th Annual Conference of the European Association for Graphics, Dublin, pp. 9--12, Sept. 2005.
• 7: H. -Y. Shum , M. Han , R. Szeliski, Interactive Construction of 3D Models from Panoramic Mosaics, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p.427, June 23-25, 1998
• 8: P. F. Sturm and S. J. Maybank. A method for interactive 3d reconstruction of piecewise planar objects from single images. Proc. British Machine Vision Conference, 1999.
• 9: L. Zhang, G. Dugas. Phocion, J. S. Samson, and S. M. Seitz. Single view modeling of free-form scenes. Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 990--997, 2001.
• 10: Hisashi Shimodaira, A Shape-from-Shading Method of Polyhedral Objects Using Prior Information, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.28 n.4, p.612, April 2006 [doi>10.1109/TPAMI.2006.67]
• 11: Jianzhuang Liu , Yong Tsui Lee, A Graph-Based Method for Face Identification from a Single 2D Line Drawing, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.23 n.10, p.1106-1119, October 2001 [doi>10.1109/34.954601 ]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.5 Reconstruction
          Subjects: Transform methods

General Terms:
Algorithms, Theory

Keywords:
image regularities, interactive 3D reconstruction, shape vector