Self-correctional 3D Shape Reconstruction from a Single Freehand Line Drawing

  • BeomSoo Oh
  • ChangHun Kim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2669)


The goal of sketch reconstruction is to take an inaccurate, 2D edge-vertex graph (i.e., sketch drawing) as input and reconstruct a 3D shape as output. However, traditional reconstruction methods based on image regularities tend to produce a distorted 3D shape. In part, this distortion is due to the inherent inaccuracies in the sketch, but it also relates to the failure to accurately distinguish between important and less important regularities.

We propose a new self-correctional reconstruction algorithm that can progressively produce refined versions of sketch reconstructions. The algorithm corrects the shape and the drawing simultaneously using geometric error metrics. The proposed algorithm can minimize the distortion of the shape by adding 3D regularities to the image regularities. The self-correctional algorithm for minimizing the distortion of sketch reconstruction is discussed, and the experimental results show that the proposed method efficiently reconstructs more accurate 3D objects than previous ones.


Pixel Noise Inherent Inaccuracy Image Regularity Freehand Sketch Vertex Constraint 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    L. Braid and P. Wang. Three-dimensional object recognition using gradient descent and the universal three-dimensional array grammar. In SPIE, volume 1607, pages 711.718, 1991.Google Scholar
  2. 2.
    R. P. Brent. Algorithms for Minimization without Derivatives. Prentice Hall, Englewood Cliffs N. J., 1973.zbMATHGoogle Scholar
  3. 3.
    D. Lamb and A. Bandopadhay. Interpreting a 3d object from a rough 2d line drawing. In Proceeding of Visualization 90, pages 59.66, 1990.Google Scholar
  4. 4.
    Y. G. Leclerc and M. A. Fiscler. An optimization based approach to the interpretation of single line drawings as 3d wire frames. Int. J. of Computer Vision, 9(2):113.136, 1992.CrossRefGoogle Scholar
  5. 5.
    H. Lipson. Computer Aided 3D Sketching for Conceptual Design, PhD Thesis. Israel Institute of Technology, Israel, 1998.Google Scholar
  6. 6.
    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.CrossRefGoogle Scholar
  7. 7.
    T. Marill. Emulating the human interpretation of line drawings as threedimensional objects. Int. J. of Computer Vision, 6(2):147.161, 1991.CrossRefGoogle Scholar
  8. 8.
    B. S. Oh and C. H. Kim. Fast reconstruction of 3d objects from single free-hand line drawing. LNCS, 2059:706.715, May 2001.Google Scholar
  9. 9.
    M. Shpitalni and H. Lipson. Identification of faces in a 2d line drawing projection of a wireframe object. IEEE Trans. Pattern Analysis & Machine Intell., 18(10):1000. 1012, 1996.Google Scholar
  10. 10.
    M. Shpitalni and H. Lipson. Classification of sketch strokes and corner detection using conic sections and adaptive clustering. Trans. of the ASME. J. of Mechanical Design, 119(2), 1997.Google Scholar
  11. 11.
    W. Wang and G. Grinstein. A survey of 3d solid reconstruction from 2d projection line drawings. In Computer Graphics Forum, pages 137.158, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • BeomSoo Oh
    • 1
  • ChangHun Kim
    • 1
  1. 1.Dept. of Computer Science and EngineeringKorea UniversitySungbuk-ku, SeoulKorea

Personalised recommendations