“Modelling from Multiple Photographs Using Points and Silhouettes” by Hawkins

  • ©Tim Hawkins

  • ©Tim Hawkins

  • ©Tim Hawkins



Entry Number: 053


    Modelling from Multiple Photographs Using Points and Silhouettes



    We present a technique for recovering a 3D model from several photographs of an object. The technique makes use of a relatively small number of user-marked image correspondences as well as usermarked silhouettes. The recovered model is well-suited for rendering with view interpolation using the original photographs as textures. A view interpolation render using this technique is featured in the SIGGRAPH 2004 Electronic Theater piece The Parthenon.


    1. Matusik, W., Buehler, C., Raskar, R., Gortler, S. J., and McMillan, L. 2000. Image-based visual hulls. In Proc. SIGGRAPH 2000, 369–374.
    2. Szeliski, R. 1993. Rapid octree construction from image sequences. CVGIP: Image Understanding 58, 1 (July), 23–32.
    3. Williams, L., and Chen, E. 1993. View interpolation for image synthesis. In SIGGRAPH 93.

Additional Images:

©Tim Hawkins


ACM Digital Library Publication:

Overview Page: