Bayesian reconstruction of 3D shapes and scenes from a single image

  title={Bayesian reconstruction of 3D shapes and scenes from a single image},
  author={Feng Han and Song-Chun Zhu},
  journal={First IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003. HLK 2003.},
It is common experience for human vision to perceive full 3D shape and scene from a single 2D image with the occluded parts "filled-in" by prior visual knowledge. We represent prior knowledge of 3D shapes and scenes by probabilistic models at two levels - both are defined on graphs. The first level model is built on a graph representation for single objects, and it is a mixture model for both man-made block objects such as trees and grasses. It assumes surface and boundary smoothness, 3D angle… CONTINUE READING
Highly Cited
This paper has 106 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 71 extracted citations

106 Citations

Citations per Year
Semantic Scholar estimates that this publication has 106 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 27 references

A mathematical teory of primal sketch ”

  • Song-Chun Zhu, Ying Nian Wu
  • Stereoscopic Segmentation ”
  • 2001

and S

  • L. Zhang, G. Dugas-Phocionz, J-S. Samsonz
  • M. Seitz “Single View Modeling of Free-Form…
  • 2001
1 Excerpt

A system for constructing boundary representation solid models from a two - dimensional sketch ”

  • S. C. Zhu
  • Proc . GMP
  • 2000

Similar Papers

Loading similar papers…