Dense 3D Reconstruction from Specularity Consistency

IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), June 2008

Diego Nehab, Tim Weyrich, Szymon Rusinkiewicz

In this work, we consider the dense reconstruction of specular objects. We propose the use of a specularity constraint, based on surface normal/depth consistency, to define a matching cost function that can drive standard stereo reconstruction methods. We discuss the types of ambiguity that can arise, and suggest an aggregation method based on anisotropic diffusion that is particularly suitable for this matching cost function.

We also present a controlled illumination setup that includes a pair of cameras and one LCD monitor, which is used as a calibrated, variable-position light source. We use this setup to evaluate the proposed method on real data, and demonstrate its capacity to recover high-quality depth and orientation from specular objects.

PDF file

Diego Nehab, Tim Weyrich, and Szymon Rusinkiewicz.
"Dense 3D Reconstruction from Specularity Consistency."
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), June 2008.

@inproceedings{Nehab:2008:D3R,
   author = "Diego Nehab and Tim Weyrich and Szymon Rusinkiewicz",
   title = "Dense {3D} Reconstruction from Specularity Consistency",
   booktitle = "IEEE Computer Society Conference on Computer Vision and Pattern
      Recognition (CVPR)",
   year = "2008",
   month = jun
}