在本篇論文中，我們提出了一個從校正好的影像得到視差圖的演算法。首先，我們將影像過度分割的應用在左圖上，沿著掃描線(如極線)找每個區塊在右圖中的對應區塊。通過計算在左右圖中區塊的顏色差，找到最佳匹配的對應區塊，則深度值即為之間的水平座標差。但並不是所有相對應的區塊都是正確對應的，因此應考慮哪些情況下的對應是正確的，並將對應錯誤的區塊去除掉。當我們有一些區塊的深度值後，我們可以透過求解線性系統的方式將這一小部分的深度值傳播到整張影像上。線性系統設置是透過一些約束，例如每個區塊的深度應和鄰近區塊的深度相類似，以及傳播的深度值應以前面步驟計算出的深度值相同。此外，我們還將此約束傳播的方法應用在影片上，所以要額外考慮影像前後深度的一致性，因此在相同的線性系統中加入了影像的運動資訊所建立的軟約束。

[1] D. Scharstein and R. Szeliski, “Middlebury stereo evaluation- version 2,” 2010, http://vision.middlebury.edu/stereo/eval/.
[2] A. Bobick and S. Intille. “Large occlusion stereo.” IJCV, 33:181–200, 1999.
[3] Y. Boykov, O. Veksler, and R. Zabih. “Fast approximate energy minimization via graph cuts.” PAMI, 2001.
[4] J. Sun, N. Zheng, and H. Y. Shum. “Stereo matching using belief propagation. ” PAMI, 2003.
[5] M. Lhuillier and L. Quan. “Match propagation for image-based modeling and rendering.” IEEE TPAMI, 2002.
[6] J. ˇCech and R. ˇS ´ara, “Efficient sampling of disparity space for fast and accurate matching.” CVPR, 2007.
[7] L. Wang and R. Yang, “Global stereo matching leveraged by sparse ground control points.” CVPR, 2011.
[8] X. Sun, X. Mei, S. Jiao, M. Zhou, H. Wang, “Stereo Matching with Reliable Disparity Propagation.” 3DIMPVT, 2011.
[9] A. F. Bobick and S. S. Intille, “Large occlusion stereo.” IJCV, 1999.
[10] Y. Wei and L. Quan, “Region-based progressive stereo matching.” CVPR, 2004.
[11] R. Khoshabeh, S. H. Chan and T. Q. Nguyen, “Spatio-temporal consistency in video disparity estimation.” ICASSP, 2011.
[12] L. Yao, D.X. Li and M. Zhang, “Temporally consistent depth maps recovery from stereo videos.” Information Technology Journal, 2012.
[13] F. Huguet and F. Devernay, “A variational method for scene flow estimation from stereo sequences.” ICCV, 2007.
[14] F. Liu and V. Philomin, “Disparity estimation in stereo sequences using scene flow.” BMVC, 2009.
[15] M. Guttmann, L. Wolf and D. Cohen-Or, “Semi-automatic Stereo Extraction from Video Footage.” ICCV, 2009.
[16] L.Valgaerts, A. Bruhn, H. Zimmer, J. Weickert, “Joint Estimation of Motion, Structure and Geometry from Stereo Sequences.” ECCV, 2010.
[17] A Fusiello, V. Roberto and E. Trucco, “Efficient stereo with multiple windowing. ” IEEE CVPR, 1997.
[18] C. Richardt, D. Orr, I.Davies, A. Criminisi, N. A. Dodgson, “Real-time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid.” ECCV, 2010.
[19] B. J. Frey and D. Dueck. “Clustering by Passing Messages between Data Points.” Science, 315:972-976, February, 2007.
[20] T.-F Su, Y.-L. Chen, and S.-H Lai, “Over-Segmentation Based Background Modeling and Foreground Detection with Shadow Removal by Using Hierarchical MRFs,” ACCV Proceedings of the 10th Asian conference on Computer vision - Volume Part III, Pages 535 – 546, 2010