Binocular Photometric Stereo

Hao Du, Dan B Goldman, and Steven M. Seitz

Binocular Photometric Stereo (BMVC'2011)


This paper considers the problem of computing scene depth from a stereo pair of cameras under a sequence of illumination directions. By integrating parallax and shading cues, we obtain both metric depth and fine surface details. Casting this problem into the filter flow framework, enables a convex formulation of the problem, and thus a globally optimal solution. We demonstrate high quality, continuous depth maps on a range of examples.

Result Comparison

Paper & Citation

Hao Du, Dan B Goldman and Steven M. Seitz. Binocular Photometric Stereo. In Proceedings of British Machine Vision Conference (BMVC), 2011 [PDF] [Poster]

Author = {Du, H. and Goldman, D. and Seitz, S.},
Title = {Binocular Photometric Stereo},
BookTitle = {Proceedings of British Machine Vision Conference (BMVC)},
Year = {2011} }

[Go to my Homepage]
Page last updated: September 19, 2012