Efficient Minimal-Surface Regularization of Perspective Depth Maps in Variational Stereo

Gottfried Graber, Jonathan Balzer, Stefano Soatto, Thomas Pock; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 511-520

Abstract


We propose a method for dense three-dimensional surface reconstruction that leverages the strengths of shape-based approaches, by imposing regularization that respects the geometry of the surface, and the strength of depth-map-based stereo, by avoiding costly computation of surface topology. The result is a near real-time variational reconstruction algorithm free of the staircasing artifacts that affect depth-map and plane-sweeping approaches. This is made possible by exploiting the gauge ambiguity to design a novel representation of the regularizer that is linear in the parameters and hence amenable to be optimized with state-of-the-art primal-dual numerical schemes.

Related Material


[pdf]
[bibtex]
@InProceedings{Graber_2015_CVPR,
author = {Graber, Gottfried and Balzer, Jonathan and Soatto, Stefano and Pock, Thomas},
title = {Efficient Minimal-Surface Regularization of Perspective Depth Maps in Variational Stereo},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}