Abstract
Stereo matching is one of the critical problems in the field of computer vision and it has been widely applied to 3D Reconstruction, Image Refocusing and etc. Recently proposed PatchMatch (PM) stereo algorithm effectively overcomes the limitation of integer-value within the support window but it is still inferior in twofold: (1) view propagation of PM stereo algorithm generally yields underwhelming particle propagation; (2) it still suffers from a coarse performance in textureless regions. To mitigate these weaknesses, a Spatial-PM stereo algorithm without view propagation is proposed for improving the original one at first. Then a virtual pixel based cost aggregation framework with two sped-up strategies is proposed for tackling the problem of textureless mismatching. Jointing the two incremental improvements, we name the novel one as Spatial PatchMatch Stereo with Virtual Pixel Aggregation (SPMVP). Experiments show that SPMVP achieves superior results than other four challenging PM based stereo algorithms both in integer & subpixel level accuracy on all 31 Middlebury stereo pairs; and also performs better on Microsoft i2i stereo videos.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vis. 47, 7–42 (2002). Springer
Gong, M., Yang, R., Wang, L., et al.: A performance study on different cost aggregation approaches used in real-time stereo matching. Int. J. Comput. Vis. 75, 283–296 (2007). Springer
Tombari, F., Mattoccia, S., Stefano, L., et al.: Classification and evaluation of cost aggregation methods for stereo correspondence. In: IEEE International Conference on Computer Vision Pattern Recognition, pp. 1–8 (2008)
Wang, L., Yang, R., Gong, M., et al.: Real-time stereo using approximated joint bilateral filtering and dynamic programming. J. Real-Time Image Proc. 9, 447–461 (2014). Springer
Taniai, T., Matsushita, Y., Naemura, T.: Graph cut based continuous stereo matching using locally shared labels. In: IEEE International Conference on Computer Vision Pattern Recognition, pp. 1613–1620 (2014)
Yang, Q., Wang, L., Ahuja, N.: A constant space belief propagation algorithm for stereo matching. In: IEEE International Conference on Computer Vision Pattern Recognition, pp. 1458–1465 (2010)
Yoon, K.J., Kweon, I.S.: Adaptive support-weight approach for correspondence search. IEEE Trans. Pattern Anal. 28, 650–656 (2006)
Hosni, A., Bleyer, M., Gelautz, M., et al.: Local stereo matching using geodesic support weights. In: IEEE International Conference Image Processing, pp. 2093–2096 (2009)
Hu, W., Zhang, K., Sun, L., et al.: Virtual support window for adaptive-weight stereo matching. In: IEEE Visual Communications and Image Processing, pp. 1–4 (2011)
Min, D., Lu, J., Do, M.N.: A revisit to cost aggregation in stereo matching: how far can we reduce its computational redundancy? In: IEEE International Conference on Computer Vision, pp. 1567–1574 (2011)
Min, D., Lu, J., Do, M.N.: Joint histogram based cost aggregation for stereo matching. IEEE Trans. Pattern Anal. 35, 2539–2545 (2013). IEEE
Bleyer, M., Breiteneder, C.: Stereo matching—state-of-the-art and research challenges. In: Farinella, G., Battiato, S., Cipolla, R. (eds.) Advanced Topics in Computer Vision. Advances in Computer Vision and Pattern Recognition. Springer, London (2013). doi:10.1007/978-1-4471-5520-1_6
Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: PatchMatch: a randomized correspondence algorithm for structural image editing. ACM Trans. Graph. 28(3), 24:1–24:11 (2009)
Bleyer, M., Rhemann, C., Rother, C.: PatchMatch stereo - stereo matching with slanted support windows. In: British Machine Vision Conference (2011)
Besse, F., Rother, C., Fitzgibbon A., et al.: PMBP: PatchMatch belief propagation for correspondence field estimation. In: British Machine Vision Conference (2012)
Heise, P., Klose, S., Jensen, B., et al.: PM-Huber: PatchMatch with huber regularization for stereo matching. In: IEEE International Conference on Computer Vision, pp. 2360–2367 (2013)
Achanta, R., Shaji, A., Smith, K., et al.: SLIC Superpixels Compared to State-of-The-Art Superpixels Methods. IEEE Trans. Pattern Anal. Mach. Intell. 34, 2274–2282 (2012). IEEE
Zhang, C., Li, Z., Cai, R., et al.: As-rigid-as-possible stereo under second order smoothness priors. In: European Conference on Computer Vision, pp. 112–126 (2014)
Zhang, K., Fang, Y., Min, D., et al.: Cross-scale cost aggregation for stereo matching. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1590–1597 (2014)
Zhang, K., Fang, Y., Min, D., et al.: Cross-scale cost aggregation for stereo matching. In: IEEE Transactions on Circuits and Systems for Video Technology (2016)
Lu, J., Yang, H., Min D., et al.: PatchMatch filter: efficient edge aware filtering meets randomized search for fast correspondence field estimation. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1854–1861 (2013)
Li, Y., Min, D., Brown, M.S., et al.: SPM-BP: sped-up PatchMatch belief propagation for continuous MRFs. In: IEEE International Conference on Computer Vision, pp. 4006–4014 (2015)
Lu, L., Shi, K., Min, D., et al.: Cross-based local multipoint filtering. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 430–437 (2012)
Christo, R., Hosni, A., Bleyer, M., et al.: Fast cost-volume filtering for visual correspondence and beyond. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 3017–3024 (2011)
Hosni, A., Christo, R., Bleyer, M., et al.: Fast cost-volume filtering for visual correspondence and beyond. IEEE Trans. Pattern Anal. 32, 504–511 (2013)
Middlebury Online Stereo Evaluation (2016). http://vision.middlebury.edu/stereo/data/
Microsoft i2i Stereo Videos (2016). http://research.microsoft.com/enus/projects/i2i/data.aspx
Acknowledgements
This research has been supported by National Natural Science Foundation of China (U1509207, 61325019, 61472278, 61403281 and 61572357), Key project of Natural Science Foundation of Tianjin (14JCZDJC31700).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Yao, P., Zhang, H., Xue, Y., Chen, S. (2017). SPMVP: Spatial PatchMatch Stereo with Virtual Pixel Aggregation. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10636. Springer, Cham. https://doi.org/10.1007/978-3-319-70090-8_54
Download citation
DOI: https://doi.org/10.1007/978-3-319-70090-8_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70089-2
Online ISBN: 978-3-319-70090-8
eBook Packages: Computer ScienceComputer Science (R0)