Line-Based Optimization for 3D Object Reconstruction from Single Line Drawings

Abstract:

Based on iterative technique, a novel optimization approach for reconstruction a planar object from a perspective line drawing is proposed. Some constraint relationships between edges of a planar object are deduced and formulated as a linear system. The planar object can be recovered by solving the linear system. If the line drawing is a practical line drawing, the recovered planar object will be re-projected onto the projective plane. And then the parameters of the projection will be weighed with those of the corresponding line in original line drawing. The new linear system can be achieved by substituting the weighted parameters into the original linear system and solved again. This procedure is iterated until the value of an object function is smaller than the threshold predefined. Experiment results show that in addition to the ideal line drawing, the proposed algorithm can be applied to the practical line drawing.

• Periodical: Applied Mechanics and Materials (Volumes 20-23)
• Pages: 910-915
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.20-23.910
• Online since: January 2010
• Authors: Jun Chu, Man Tun Gao, Gui Mei Zhang, Rui Na Feng
• Keywords: 3D Reconstruction, Based-Line Optimization, Iterative, Line Drawing

References

[1] J. Z. Liu, L. L. Cao, Z. G. Li and X. O. Tang, Plane-Based Optimization for 3D Object Reconstruction from single line drawings, IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2): 315-327, (2008).

DOI: 10.1109/tpami.2007.1172

[2] M. C. Cooper, Wireframe Projections: Physical Realisability of Curved Objects and Unambiguous Reconstruction of Simple Polyhedral, International Journal of Computer Vision, 64(1): 69-88, (2005).

DOI: 10.1007/s11263-005-1087-9

[3] M. C. Cooper, The Interpretations of Line Drawings with Contrast Failure and Shadows, International Journal of Computer Vision, 43(2): 75-97, (2001).

[4] M. Shpitalni and H. Lipson, Identification of Faces in a 2D Line Drawing Projection of a Wireframe Object, IEEE Transaction on Pattern Analysis and Machine Intelligence, 18(10): 1000-1012, (1996).

DOI: 10.1109/34.541409

[5] J. Liu, Y. T. Lee and W. Cham, Identifying Faces in a 2D Line Drawing Representing a Manifold Object, IEEE Transactions On Pattern Analysis and Machine Intelligence, 24(12): 1579-1593, (2002).

DOI: 10.1109/tpami.2002.1114850

[6] J. Liu and X. Tang, Evolutionary Search for Faces from Line Drawings, IEEE Transaction on Pattern Analysis and Machine Intelligence, 27(6): 861-872, (2005).

DOI: 10.1109/tpami.2005.119

[7] H. Li, nD Polyhedral Scene Reconstruction from Single 2D Line Drawing by Local Propagation, Lecture Notes in Artificial Intelligence, 3763: 169-197, (2006).

DOI: 10.1007/11615798_11

[8] H. Lipson and M. Shpitalni, Optimization-Based Reconstruction of a 3D Object from a Single Freehand Line Drawing, Computer-Aided Design, 28(8): 651-663, (1996).

DOI: 10.1016/0010-4485(95)00081-x

[9] P. Company, M. Contero, J. Conesa, and A. Piquer, An Optimization-Based Reconstruction Engine for 3D Modeling by Sketching, Computers & Graphics, 28(6): 955-979, (2004).

DOI: 10.1016/j.cag.2004.08.007

[10] P. A. C. Varley and R. R. Martin, Estimating Depth from Line Drawings, Proceedings of the Seventh ACM Symposium on Solid Modeling and Applications, Saarbrücken, Germany , 180-191, (2002).

DOI: 10.1145/566282.566310

[11] J. Chu, M. T. Gao and G. D. Chen, "Creating Model of Plane Body from Line Drawing Under Perspective Projection, Xibei Gongye Daxue Xuebao, 22(1): 84-87, (2004).

[12] G. M. Zhang, M. T. Gao and Y. W. Shen, Recognition of Partially Occluded Polygon From Line Drawing, Pattern recognition and artificial intelligence, 20(1): 124-130, (2007).

[13] J. Chu and M. T. Gao, Recovering the Shape of Planar Object Depicted by a Line Drawing under Axonometric Projection, Computer Aided Drafting, Design and Manufacturing, 15(1): 29-35, (2005).