3D Plane Labeling Stereo Matching with Content Aware Adaptive Windows

Luis Horna, Robert B. Fisher

2017

Abstract

In this paper, we present an algorithm that exploits both the underlying 3D structure and image entropy to generate an adaptive matching window. The presented algorithm estimates real valued disparity maps by smartly exploring a 3D search space using a novel hypothesis generation approach that acts like a propagation scheduler. The proposed approach is among the top performing results when evaluated in the Middlebury, KITTI 2015 benchmarks.

References

  1. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., and S üsstrunk, S. (2012). Slic superpixels compared to state-of-the-art superpixel methods. PAMI, 34(11):2274-2282.
  2. Besse, F., Rother, C., Fitzgibbon, A., and Kautz, J. (2012). Pmbp: Patchmatch belief propagation for correspondence field estimation. International Journal of Computer Vision, 110(1):2-13.
  3. Bleyer, M., Rhemann, C., and Rother, C. (2011). Patchmatch stereo - stereo matching with slanted support windows. In Proceedings of the British Machine Vision Conference, 11:1-11.
  4. Geiger, A., Lenz, P., and R.Urtasun (2012). Are we ready for autonomous driving? the kitti vision benchmark suite. CVPR, pages 3354-336.
  5. Guney, F. and Geiger, A. (2015). Displets: Resolving stereo ambiguities using object knowledge. CVPR.
  6. Heise, P., Klose, S., Jensen, B., and Knoll, A. (2013). Patchmatch with huber regularization for stereo matching. ICCV, pages 2360-2367.
  7. Klaus, A., Sormann, M., and Karner, K. (2006). Segmentbased stereo matching using belief propagation and a self-adapting dissimilarity measure. ICPR, 3:15-18.
  8. Kolmogorov, V. (2007). Convergent tree-reweighted message passing for energy minimization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(10):1568-1583.
  9. Kolmogorov, V. and Zabih, R. (2001). Computing visual correspondence with occlusions using graph cuts. ICCV, 2:508-515.
  10. Li, A., Chen, D., Liu, Y., and Yuan, Z. (2016a). Coordinating multiple disparity proposals for stereo computation. CVPR.
  11. Li, L., Zhang, S., Yu, X., and Zhang, L. (2016b). Pmsc: Patchmatch-based superpixel cut for accurate stereo matching. IEEE Transactions on Circuits and Systems for Video Technology.
  12. Li, Y., Min, D., Brown, M. S., Do, M. N., and Lu, J. (2015). Sped-up patchmatch belief propagation. ICCV.
  13. Menze, M. and Geiger, A. (2015). Object scene flow for autonomous vehicles. CVPR.
  14. Olsson, C., Ulén, J., and Boykov, Y. (2013). In defense of 3d-label stereo. CVPR, pages 1730-1737.
  15. Park, M.-G. and Yoon, K.-J. (2016). As-planar-as-possible depth map estimation. Submitted to IEEE TPAMI.
  16. Scharstein, D., Hirschmüller, H., Kitajima, Y., Krathwohl, G., Nesic, N., Wang, X., and Westling, P. (2014). High-resolution stereo datasets with subpixel-accurate ground truth. In German Conference on Pattern Recognition (GCPR), pages 31-42.
  17. Sinha, S., Scharstein, D., and Szeliski, R. (2014). Efficient high-resolution stereo matching using local plane sweeps. CVPR, pages 1582-1589.
  18. Taniai, T., Matsushita, Y., and Naemura, T. (2014). Graph cut based continuous stereo matching using locally shared labels. CVPR, pages 1613-1620.
  19. Vedaldi, A. and Fulkerson, B. (2008). VLFeat: An open and portable library of computer vision algorithms. http://www.vlfeat.org/.
  20. Vedaldi, A. and Soatto, S. (2008). Quick shift and kernel methods for mode seeking. ECCV, 5305:705-718.
  21. Vogel, C., Schindler, K., Konrad, and Roth, S. (2015). 3d scene flow estimation with a piecewise rigid scene model. IJCV, pages 1-28.
  22. Z?bontar, J. and LeCun, Y. (2015). Stereo matching by training a convolutional neural network to compare image patches. Submitted to JMLR.
  23. Woodford, O. J., Reid, I. D., Torr, P. H. S., and Fitzgibbon, A. W. (2007). On new view synthesis using multiview stereo. In Proceedings of the British Machine Vision Conference, pages 1-10.
  24. Yamaguchi, K., McAllester, D., and Urtasun, R. (2014). Efficient joint segmentation, occlusion labeling, stereo and flow estimation. ECCV, pages 756-771.
  25. Yoon, K. and Kweon, I. (2006). Adaptive support-weight approach for correspondence search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(4):650-656.
  26. Zabih, R. and Li, J. (1994). Non-parametric local transforms for computing visual correspondence. ECCV, 12:151-158.
  27. Zhang, C., Li, Z., Cheng, Y., Cai, R., Chao, H., and Rui, Y. (2015). Meshstereo: A global stereo model with mesh alignment regularization for view interpolation. ICCV.
  28. Zhang, K., Lu, J., and Lafruit, G. (2009). Cross-based local stereo matching using orthogonal integral images. IEEE Transactions on Circuits and Systems for Video Technology, 19(7):1073-1079.
Download


Paper Citation


in Harvard Style

Horna L. and B. Fisher R. (2017). 3D Plane Labeling Stereo Matching with Content Aware Adaptive Windows . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-227-1, pages 162-171. DOI: 10.5220/0006105401620171


in Bibtex Style

@conference{visapp17,
author={Luis Horna and Robert B. Fisher},
title={3D Plane Labeling Stereo Matching with Content Aware Adaptive Windows},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={162-171},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006105401620171},
isbn={978-989-758-227-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)
TI - 3D Plane Labeling Stereo Matching with Content Aware Adaptive Windows
SN - 978-989-758-227-1
AU - Horna L.
AU - B. Fisher R.
PY - 2017
SP - 162
EP - 171
DO - 10.5220/0006105401620171