傳統的立體匹配演算法可大致被分為兩大類，一種為全域性演算法，需要透過能量函式的最佳化來求得視差值；另一種為區域性演算法，是以點為基礎參考周遭資訊來決定視差值，現在為了實際應用所需，區域性演算法是較主流的方法。然而區域性演算法因為只採納周遭部分資訊，相較於全域性演算法而言在某些區域較容易發生錯誤，如重複紋理、平坦區域。因此在本篇論文中，提出了一個新的成本建構方式，結合顏色和梯度並採用決策機制，藉此改善重複紋理區域。且在生長支持區域的動態閥值設定，使得支持區域更加貼近物體形狀，以盡可能地收集到最多的資訊。最後利用成本曲線的局部最小值特性搭配視差傳遞的方法，解決剩餘易錯區域的錯誤。
　　此外，對於現在高解析度影像的普及，本篇論文也採用了超解析的技術解決深度圖解析度不足的問題，使用了 [1]提出的雙邊濾波器保留高解析度彩圖邊界的方式提升深度圖的解析度，用來解決高解析影像的計算問題。
　　本論文所提出的方法均可利用GPU平行處理以提升整體效能。

　　Traditional stereo matching algorithms can be roughly categorized into two classes: global methods and local methods. Global methods use the information of whole image and obtain depth image through optimization of the energy function. On the contrary, local methods only use the information of neighbor area and are faster and popular in mainstream for real application.
　　However, local methods are more prone to error in some areas, such as lighting changes, repeated textures, and smooth area. Therefore, in this paper we propose new cost architecture which combine color and gradient and adopt a selection scheme, whereby resist the impact of lighting change and correct the error in repeated texture region. Besides, the support region is generated by dynamic threshold to span the region more close to object contour, and aggregate the information as many as possible. In refinement, we use the properties of local minimum to detect the error-prone area, and correct the error with disparity propagation.
　　In addition, nowadays the popularity of high-resolution images, we also use the technology of super resolution to solve the problem of depth image with insufficient resolution.
　　Each step of the algorithm can utilize GPU parallel processing to improve overall performance.

[1] Q. Yang, R. Yang, J. Davis and D. Nistér, "Spatial-Depth Super Resolution for Range Images," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2007.
[2] W. Y. Chen, Y. L. Chang, S. F. Lin and L. F. Di, "Efficient depth image based rendering with edge dependent depth filter and interpolation," IEEE International Conference on Multimedia and Expo., pp. 1314-1317, 2005.
[3] D. Scharstein and R. Szeliski, "A taxonomy and evaluation of dense two-frame stereo correspondence algorithms," IJCV, vol. 47, no. 1-3, pp. 7-42, 2002.
[4] Y. Boykov, O. Veksler and R. Zabih, "Fast approximate energy minimization via graph cuts," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1222-1239, 2001.
[5] V. Kolmogorov and R. Zabih, "Computing Visual Correspondence with Occlusions Using Graph Cuts," in IEEE International Conference on Computer Vision, vol.2, pp. 508-515, 2001.
[6] G. Chen and L. Hong, "Segment-based stereo matching using graph cuts," IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. I-74-I-81, 2004.
[7] J. Sun, N. N. Zheng and H. Y. Shum, "Stereo Matching Using Belief Propagation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 7, pp. 787-800, July 2003.
[8] Q. Yang, L. Wang, R. Yang and H. Stewen, "Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation, and Occlusion Handling," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. vol.31, no. 3, pp. 492-504, 2009.
[9] M. S. a. K. K. Andreas Klaus, "Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure," in International Conference on Pattern Recognition, vol.3, pp. 15-18, 2006.
[10] O. Veksler, "Stereo correspondence by dynamic programming on a tree," IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 384-390, 2005.
[11] X. Sun, X. Mei, S. Jiao, M. Zhou and H. Wang, "Stereo Matching with Reliable Disparity Propagation," in International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, 2011.
[12] K. J. Yoon and S. Kweon, "Adaptive Support-Weight Approach for Correspondence Search," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 650-656, 4 2006.
[13] A. Hosni, M. Bleyer, Rhemann, M. Gelautz and Christoph, "Local Stereo Matching Using Geodesic Support Weights," in IEEE International Conference on Image Processing (ICIP), 2009.
[14] K. Zhang, J. Lu and G. Lafruit, "Cross-Based Local Stereo Matching Using Orthogonal Integral Images," in IEEE Transactions on circuit and systems for video technology, vol. 19, no. 7, 2009.
[15] X. Mei, X. Sun, M. Zhou, S. Jiao, H. Wang and X. Zhang, "On Building an Accurate Stereo Matching System on Graphics Hardware," in IEEE International Conference on Computer Vision Workshops, 2011.
[16] D. Scharstein and R. Szeliski, "http://vision.middlebury.edu/stereo/eval/," Middlebury stereo evaluation - version 2, 2010.
[17] R. Zabih and J. Woodfill, "Non-parametric local transforms for computing visual correspondence," in European conference on Computer Vision, pp. 151-158, 1994.
[18] I. E. Sobel, "Camera models and machine perception," Doctoral Dissertation, 1970.
[19] X. Chen and H. Chen, "A Novel Color Edge Detection Algorithm in RGB Color Space," in IEEE 10th International Conference on Signal Processing, 2010.
[20] A. Ansar, A. Castano and L. Matthies, "Enhanced real-time stereo using bilateral filtering," 3D Data Processing, Visualization and Transmission, pp. 455 - 462, 2004.
[21] X. Zhang, Y. Shen and L. Hu, "Super-Resolution Reconstruction Algorithm for PMD Range Image Based on Regularization," in International Conference on Intelligent Human-Machine Systems and Cybernetics, Hangzhou, China, 2011.
[22] S. S, T. C and D. J, "High-quality Scanning Using Time-of-flight Depth Super-Resolution," in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Anchorage,USA, 2008.
[23] S. S, T. C and D. J, "Depth Super-Resolution for ToF 3D Shape Scanning," in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009.
[24] D. J and T. S, "An Application of Markov Random Fields to Range Sensing," in Advances in Neural Information Processing Systems, Vancouver, Canada, 2005.
[25] J. Lu, D. Min and R. S. Pahwa, "A Revisit to MRF-Based Depth Map Super-Resolution and Enhancement," in IEEE International Conference on Acoustics, Speech and Signal Processing, Prague, Czech Republic, 2011.
[26] K. J, C. M F and D. Lischinski, "Joint Bilateral Upsampling," in ACM Trans on Graphics, 2007.
[27] H. Hirschm¨uller, "Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 807 - 814, 6 2005.