Multiple Depth Maps Integration for 3D Reconstruction Using

Geodesic Graph Cuts

International Journal of Software Engineering and Knowledge Engineering

Fig1 Reconstruction results on benchmark data sets. The first row displays the color images used in our reconstruction approach. The second row gives the results obtained with original graph cuts method using surfel representation[1]. The third row gives the models reconstructed using our proposed approach. Red boxes are used to highlight the differences between the two group of results.

Fig2 Reconstructed model using different methods: (a) is the result generated using state-of-art range images integration [2], (b) is the result using graph-cut [3], (c) gives the reconstructed model from graph-cut yet with our proposed adaptive regional term, respectively; (d) is the rendered results of (c).

Abstract:

Depth images, in particular depth maps estimated from stereo vision, may have a substantial amount of outliers and result in inaccurate 3D modelling and reconstruction. To address this challenging issue, in this paper, a graph-cut based multiple depth maps integration approach is proposed to obtain smooth and watertight surfaces. First, confidence maps for the depth images are estimated to suppress noise, based on which reliable patches covering the object surface are determined. These patches are then exploited to estimate the path weight for 3D geodesic distance computation, where an adaptive regional term is introduced to deal with the "shorter-cuts" problem caused by the effect of the minimal surface bias. Finally, the adaptive regional term and the boundary term constructed using patches are combined in the graph-cut framework for more accurate and smoother 3D modelling. We demonstrate the superior performance of our algorithm on the well-known Middlebury multi-view database and additionally on real world multiple depth images captured by Kinect. The experimental results have shown that our method is able to preserve the object protrusions and details while maintaining surface smoothness.

Citation:

References:

[1] J. Y. Chang, H. Park, I. K. Park et al., GPU-friendly multi-view stereo reconstruction using surfel representation and graph cuts. In CVIU, 2011.

[2] B. Curless and M. Levoy, A volumetric method for building complex models from range images, In Computer Graphics and Interactive Techniques, 1996.

[3] G. Vogiatzis, P. H. S. Torr and R. Cipolla, Multi-view stereo via volumetric graph-cuts. In CVPR, 2005.