Abstract
We propose a graph-based semi-supervised symmetric matching framework that performs dense matching between two uncalibrated wide-baseline images by exploiting the results of sparse matching as labeled data. Our method utilizes multiple sources of information including the underlying manifold structure, matching preference, shapes of the surfaces in the scene, and global epipolar geometric constraints for occlusion handling. It can give inherent sub-pixel accuracy and can be implemented in a parallel fashion on a graphics processing unit (GPU). Since the graphs are directly learned from the input images without relying on extra training data, its performance is very stable and hence the method is applicable under general settings. Our algorithm is robust against outliers in the initial sparse matching due to our consideration of all matching costs simultaneously, and the provision of iterative restarts to reject outliers from the previous estimate. Some challenging experiments have been conducted to evaluate the robustness of our method.
Chapter PDF
Similar content being viewed by others
Keywords
- Graphic Processing Unit
- Image Space
- Stereo Match
- Locally Linear Embedding
- Graphic Processing Unit Implementation
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: Proceedings of IEEE Conference Computer Vision and Pattern Recognition, vol. 1, pp. 519–528 (2006)
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision 47(1-3), 7–42 (2002)
Strecha, C., Fransens, R., Gool, L.: Wide-baseline stereo from multiple views: a probabilistic account. In: Proceedings of IEEE Conference Computer Vision and Pattern Recognition, vol. 1, pp. 552–559 (2004)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)
Toshev, A., Shi, J., Daniilidis, K.: Image matching via saliency region correspondences. In: Proceedings of IEEE Conference Computer Vision and Pattern Recognition, pp. 1–8 (2007)
Lhuillier, M., Quan, L.: Match propagation for image-based modeling and rendering. IEEE Transaction on Pattern Analysis and Machine Intelligence 24(8), 1140–1146 (2002)
Kannala, J., Brandt, S.S.: Quasi-dense wide baseline matching using match propagation. In: Proceedings of IEEE Conference Computer Vision and Pattern Recognition, pp. 1–8 (2007)
Roth, S., Black, M.J.: Fields of experts: A framework for learning image priors. In: Proceedings of IEEE Conference Computer Vision and Pattern Recognition, vol. 2, pp. 860–867 (2005)
Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)
Ham, J., Lee, D., Saul, L.K.: Learning high dimensional correspondences from low dimensional manifolds. In: Proceedings of International Conference on Machine Learning (2003)
Hartley, R., Zisserman, A.: Multiple view geometry in computer vision, 2nd edn. Cambridge University Press, Cambridge (2004)
Sun, J., Li, Y., Kang, S.B., Shum, H.Y.: Symmetric stereo matching for occlusion handling. In: Proceedings of IEEE Conference Computer Vision and Pattern Recognition, vol. 2, pp. 399–406 (2005)
Krüger, J., Westermann, R.: Linear algebra operators for GPU implementation of numerical algorithms. ACM Transactions on Graphics, 908–916 (2003)
Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Schölkopf, B.: Learning with local and global consistency. Neural Information Processing Systems 16, 321–328 (2004)
Wang, F., Wang, J., Zhang, C., Shen, H.: Semi-supervised classification using linear neighborhood propagation. In: Proceedings of IEEE Conference Computer Vision and Pattern Recognition, pp. 160–167 (2006)
Hoiem, D., Stein, A., Efros, A., Hebert, M.: Recovering occlusion boundaries from a single image. In: Proceedings of IEEE International Conference on Computer Vision (2007)
Tola, E., Lepetit, V., Fua, P.: A fast local descriptor for dense matching. In: Proceedings of IEEE Conference Computer Vision and Pattern Recognition, pp. 1–8 (2008)
Lhuillier, M., Quan, L.: A quasi-dense approach to surface reconstruction from uncalibrated images. IEEE Transaction on Pattern Analysis and Machine Intelligence 27(3), 418–433 (2005)
Quan, L.: Invariant of six points and projective reconstruction from three uncalibrated images. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(1), 34–46 (1995)
**ao, J., Chen, J., Yeung, D.Y., Quan, L.: Structuring visual words in 3D for arbitrary-view object localization. In: Proceedings of European Conference on Computer Vision (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
**ao, J., Chen, J., Yeung, DY., Quan, L. (2008). Learning Two-View Stereo Matching. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5304. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88690-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-540-88690-7_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88689-1
Online ISBN: 978-3-540-88690-7
eBook Packages: Computer ScienceComputer Science (R0)