超高解析度(3840 2160)的螢幕在2014年美國消費性電子展(CES)中被視為下一個世代的主流顯示器。此外，現今的立體影像技術發展也越趨成熟，隨著3D顯示產品的發展，相較於傳統穿戴式配件的3D顯示技術，裸眼立體顯示器不需配戴眼鏡便可瀏覽多視角立體影像，給予多人可觀賞且舒適的視聽環境。本論文提出了一個基於動態視差選擇的即時視訊撥放系統，支援超高解析度螢幕並且可以符合多樣性立體螢幕之多視角合成。這個系統以立體匹配以及深度繪圖演算法為基礎，搭配繪圖處理器(GPU)的平行運算，透過不同的樣板影像輔助，可將雙視角視訊合成出符合各種顯示輸出的多視角合成影像。本論文提出動態視差選擇演算法選擇最適用之視差，本系統亦可隨時根據使用者喜好設定，調整立體影像的效果，提供多樣化的3D效果選擇。

The 3D techniques have been developed maturely in recent years. Compared with the traditional 3D displays with 3D glasses, the autostereoscopic 3D display provides more comfortable and unrestricted environment. Nowadays, the ultra-high definition also becomes more and more popular. This thesis proposes a comfortable two-view to multi-view conversion system with candidate disparity selection. The proposed system can afford the various autostereoscopic monitors with the ultra HD resolution. The proposed system is based on stereo matching and DIBR to generate the virtual view. The proposed system with GPU acceleration executes efficiency. The candidate disparity selection gathers the most important disparity for the stereo matching. The system gives the 3D setting for users to adjust 3D effects according to the viewer demand.

[1] M. H. Chia and W. K. Liu, “Two view to n-view conversion without depth,” Visual Communications and Image Processing (VCIP), 2011 IEEE, Nov. 2011, pp. 1–4.
[2] S. Mashhour and A. Ghassan, “Depth-less 3D rendering,” Signals, Systems and Computers (ASILOMAR), 2012 Conference Record of the Forty Sixth Asilomar Conference on, Nov. 2012, pp. 1058–6393.
[3] D. Piotr, S. A. Pitchaya, F. William, D. Frédo, and M. Wojciech, “Joint view expansion and filtering for automultiscopic 3D displays,” ACM Transactions on Graphics, Vol. 32, No. 6, Article 221, Publication Date: November 2013.
[4] C. Fehn , "Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV", Proc. of SPIE 5291, Stereoscopic Displays and Virtual Reality Systems XI, May 21, 2004.
[5] J. Sun, N. N. Zheng, and H. Y. Shum, “Stereo matching using belief propagation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, pp. 787–800, Jul. 2003.
[6] Y. Boykov, O. Veksler, and R. Zabih, “Fast Approximate energy minimization via graph cuts,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 23, pp. 1222–1239, Nov. 2001.
[7] X. Sun, X. Mei, S. Jiao, M. Zhou, and H. Wang, “Stereo matching with reliable disparity propagation,” in Proc. Int. Conf. 3D Image, Model. Process. Vis. Transm., May 2011, pp. 132–139.
[8] S. B. Kang, R. Szeliski, and J. Chai, “Handling occlusions in dense multi-view stereo,” in Proc. IEEE Comp. Soc. Conf. Comp. Vis. Pattern Recognit., vol. 1, 2001, pp. 103–110.
[9] Veksler, “Fast variable window for stereo correspondence using integral images,” in Proc. IEEE Comp. Soc. Conf. Comp. Vis. Pattern Recognit., vol. 1, Jun. 2003, pp. 556–561.
[10] K. J. Yoon and I. S. Kweon, “Adaptive Support-weight Approach for Correspondence Search,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no.4, pp. 650–656, 2006.
[11] K. Zhang, J. Lu, and G. Lafruit, “Cross-based local stereo matching using orthogonal integral images,” IEEE Trans. Circuits Syst. Video Technol., vol. 19, pp. 1073–1079, Jul. 2009.
[12] Christoph Fehn, “Depth-image-based rendering (DIBR), compression and transmission for a new approach on 3D-TV,” Proceedings of SPIE: Stereoscopic Displays and Virtual Reality Systems XI, vol. 5291, pp. 93–104, May 21, 2004.
[13] P. J. Lee and Effendi, “Nongeometric distortion smoothing approach for depth map preprocessing,” IEEE Transactions on Multimedia, vol. 13, no. 2, pp. 246–254, April 2011.
[14] B. Marcelo, S. Guillermo, C. Vicent and B. Coloma, “Image inpainting,” Proceedings of ACM SIGGRAPH, Intern. Conference on Computer Graphics and Interactive Techniques, vol. 174, pp. 417–424, New Orleans, LA, July 2000.
[15] Y. C. Yeh, “A search-based stereoscopic to multi-view video translation system with GPU realization,” Thesis for Master of Science, Nation Cheng Kung University, 2014
[16] R. Christian, Z. Frederik, K. Peter, G. Jens, S. Ralf, “fully automatic stereo-to-multiview conversion in autostereoscopic displays,” The Best of IET and IBC 09/2012; 4:8–14.
[17] J. W. Shin, “Fast disparity estimation based on cost-reproduced local stereo matching for high resolution video sequence,” Thesis for Master of Science, Nation Cheng Kung University, 2014.
[18] Y. H. Chen, “A high efficient GPU-based multiview rendering system for ultra high definition 3D displays,” Thesis for Master of Science, Nation Cheng Kung University, 2014.
[19] J. Choi, D. Min and K. Sohn,"Reliability-based multiview depth enhancement considering interview coherence", IEEE Transaction on Circuits and Systems for Video Technology, Vol. 24, No 4, pp. 603, April 2014.
[20] S. M. Seitz, B. Curless, J. Diebel, D. Scharstein, R. Szeliski, "A comparison and evaluation of multi-view stereo reconstruction algorithm", Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, June 2006.
[21] "David Laser scanner tests" on Augmented stage, a website for the research group Virtual Theatre http://www.talltreelabs.org/wordpress/?p=23
[22] S. B. Lee and Y. S. Ho, "Discontinuity-adaptive depth map filtering for 3D view generation", Proceedings of the 2nd International Conference on Immersive Telecommunications, Article No.8, May 2009.
[23] K. Mu¨ller , "3-D video representation using depth maps", Proceedings of the IEEE, Vol. 99, No. 4, April 2011.
[24] X. Xu, L. M. Po, C. H. Cheung, L. Feng, K. H. Ng and K. W. Cheung, "Depth-aided exemplar-based hole filling for DIBR view synthesis", 2013 IEEE International Symposium on Circuits and Systems(ISCAS), pp2840–2843,May 2013.
[25] NVIDIA Computer Vision Corporation Website:
http://www.nvidia.com.tw/page/home.html
[26] NVIDIA DEVELOPER ZONE: CUDA C Programming Guide http://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#axzz34Vc9Eacv
[27] M. Morisita, “Measuring of interspecific association and similarity between communities”. Mem. Fac. Sci. Kyushu Univ. Ser. E (Biol.) 3:65–80, 1959.
[28] H. C. Tseng, “Efficient 3D video packing and comfort disparity modification for traditional broadcasting systems,” Thesis for Master of Science, Nation Cheng Kung University, 2013.
[29] Microsoft Developer Network http://msdn.microsoft.com/en-US/