現今立體影像技術發展愈趨成熟，相關的3D顯示產品也日新月異，然而比照傳統3D顯示須穿戴眼鏡式的3D配件，裸眼立體顯示器提供符合多人觀賞的舒適環境。因此，裸眼3D技術勢必成為未來的趨勢。而提供多視角影像資訊可使人觀賞不同角度的立體影像。本論文旨在提出一個以搜尋式為基礎的雙視角轉多視角影像播放系統，搭配繪圖處理器(GPU)平行化加速處理，透過螢幕樣版的特殊排點，經由搜尋式演算法完成立體多視角生成系統。此系統提供豐富的視角資訊，並可提供視差選擇模式以匹配使用者想要的3D效果。

Nowadays, 3D techniques and 3D products have been developed maturely for years. The autostereoscopic multiview displays provide more comfortable environments than the traditional 3D displays with 3D glasses. Therefore, naked-eye techniques must be the trend of future development. The thesis proposes a search-based stereoscopic to multi-view translation (SSMT) playing system based on the traditional depth-image based rendering (DIBR) algorithm. Applying with graphic processing unit (GPU), this system effectively arranges the computation loads executed in parallel. With the arrangement on sub-pixels of the template, it completes the multi-view translation system using a search-based algorithm. It provides abundant of view information and an optional 3D factor mode to fit personal requirements.

[1] Daniel Minoli,"3DTV Content Capture, Encoding and Transmission" John Wiley & Sons, Inc., Hoboken, New Jersey, August 2010.
[2] CNET : LED LCD vs. plasma vs. LCD:
http://www.cnet.com/news/led-lcd-vs-plasma-vs-lcd/
[3] Jinwook Choi, Dongbo Min and Kwanghoon 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.
[4] Steven M.Seitz, Brian Curless, James Diebel, Daniel Scharstein, Richard 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.
[5] "David Laser scanner tests" on Augmented stage, a website for the research group Virtual Theatre http://www.talltreelabs.org/wordpress/?p=23
[6] Kuk-Jin Yoon and In So Kweon, "Adaptive Support-Weight Approach for Correspondences Search", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No. 4, April 2006.
[7] Jiangbo Lu, Ke Zhang, Gauthier Lafrui and Francky Catthoor, "Real-time stereo matching: A cross-based local approach", IEEE International Conference on ICASSP, pp. 733~736, April 2009.
[8] NVIDIA Computer Vision Corporation Website:
http://www.nvidia.com.tw/page/home.html
[9] Karsten Mu¨ller , "3-D Video Representation Using Depth Maps", Proceedings of the IEEE, Vol. 99, No. 4, April 2011.
[10] Sang-Beom Lee and Yo-Sung Ho, "Discontinuity-adaptive Depth Map Filtering for 3D View Generation", Proceedings of the 2nd International Conference on Immersive Telecommunications, Article No.8, May 2009.
[11] Xuyuan Xu, Lai-Man Po, Chun-Ho Cheung, Litong Feng, Ka-Ho Ng and Kwnok-Wai Cheung, "Depth-aided exemplar-based hole filling for DIBR view synthesis", 2013 IEEE International Symposium on Circuits and Systems(ISCAS), pp2840-2843,May 2013.
[12] Something More for Research, Explorer of Research in Information Technology: CPU versus GPU performance.
https://hemprasad.wordpress.com/category/project-related/
[13] OpenCL by Khronos Group http://www.khronos.org/opencl/
[14] Rage3D.com: Discussing GERORCE 8-SERIES http://ns1.rage3d.com/reviews/video/nvidia8800/index.php?p=2
[15] Lu Wang, Ju Liu, Jiande Sun, Yannan Ren, Wei Liu and Yuling Gao, "Visual view synthesis without preprocessing depth image for depth image based rendering", Proc. of 2011 3DTV Conference: The True Vision –Capture, Transmission and Display of 3D Video(3DTV-CON), May 2011.
[16] Xing Mei, Xun Sun, Mingcai Zhou, Shaohui Jiao, Haitao Wang and Xiaopeng Zhang, "On Building an Accurate Stereo Matching System on Graphics Hardware", Proc. of 2011 IEEE International Conference on Computer Vision Workshops(ICCV Workshops), pp467~474, November 2011
[17] OpenCV: Open Source Computer Vision , designed for computational efficiency and with a strong focus on real-time applications. http://opencv.org/
[18] Microsoft Developer Network http://msdn.microsoft.com/en-US/