裸眼立體顯示器不必配戴眼鏡即可瀏覽多視角立體影像的觀賞模式，給予人們更舒適的視聽環境，因此裸眼立體螢幕被視為下一個世代的主流立體顯示技術。由於多視角拍攝設備的缺乏，如何透過二維至三維影像轉換的技術將傳統二維資訊經由影像處理轉換為立體螢幕使用的三維影像成為重要的研究項目。本論文旨在提出一個符合多樣性立體螢幕的即時視訊撥放系統，這個系統以深度繪圖演算法為基礎，開發一個適應性多視角合成演算法，透過一樣板影像輔助可將一單視角單深度視訊即時繪製成符合各種顯示輸出的多視角合成影像。另外本系統可以隨時根據使用者的喜好調整立體顯像效果，提供一個更個性化的觀賞品質。

Naked-eye stereo displays provide a renovation of vision experiences; audiences can enjoy more comfortable and unrestricted multiview 3D entertainment without the aid of stereo glasses, therefore the naked-eye stereo display is considered the major 3D displaying technique in next generation. Due to the lack of native multiview shooting devices, how to transfer conventional 2D information into the proper format that the stereo display utilizes through 2D-to-3D conversion is an important research topic. The goal of this thesis focuses on building a rendering system which could synthesize multiview 3D images satisfying versatile stereo displays from a one-view-plus-depth sequence; the proposed system employs the idea of depth image-based rendering ( DIBR ) to develop a template-based adaptive multiview rendering ( TAMR ) algorithm. The system can adjust 3D effects which viewers desire immediately; on the other hand it offers a more personal vision experience.

[1] L. Lipton, "StereoGraphics Developers’ Handbook," StereoGraphics Corporation, San Rafael, CA, 1997.
[2] Karsten Mu¨ller , "3-D Video Representation Using Depth Maps", Proceedings of the IEEE, Vol. 99, No. 4, April 2011
[3] A. Smolic, K. Mueller and P. Merkle, "3D Video And Free Viewpoint Video – Technologies, Appli Cations And Mpeg Standards", Multimedia and Expo, IEEE International Conference on, pp. 9-12 July 2006
[4] Masayuki Tanimoto, "Overview of free viewpoint television", Signal Processing: Image Communication, Vol. 21, Issue 6, pp. 454–461, July 2006
[5] C. Fehn, P. Kauff, "An Evolutionary And Optimised Approach on 3D-TV", Proceedings IBC'02, pp. 357-365, 2002
[6] S. A. Valencia and R. M. Rodriguez-Dagnino, "Synthesizing stereo 3D views from focus cues in monoscopic 2D images," Proceedings of SPIE, Vol. 5006, pp. 377-388, 2003.
[7] Y. Feng, J. Ren , "Object-Based 2D-to-3D Video Conversion for Effective Stereoscopic Content Generationin 3D-TV Applications",IEEE Transactions on Broadcasting, Vol. 57, No. 2, June 2011
[8] H. M, Wang, C. H. Huang and J. F. Yang, "Depth maps interpolation from existing pairs of keyframes and depth maps for 3D video generation ," Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 3248-3251, May 30-June 2, 2010.
[9] K.J. Yoon, I.S. Kweon, "Adaptive Support-Weight Approach for Correspondence Search", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No. 4, April 2006
[10] C. Fehn , "Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV", Proc. SPIE 5291, Stereoscopic Displays and Virtual Reality Systems XI, May 21, 2004
[11] L. Zhang, W. J. Tam, and D. Wang, "Stereoscopic image generation based on depth images, " in Proc. IEEE Int. Conf. Image Process. (ICIP 04), 2004, pp. 2993–2996.
[12] L. Zhang and W. J. Tam, "Stereoscopic image generation based on depth images for 3DTV, "IEEE Trans. Broadcasting, Vol. 51, no. 2, pp.191–199, Jun. 2005.
[13] L.H. Wang and X.J. Huang, " An Asymmetric Edge Adaptive Filter for Depth", IEEE TRANSACTIONS ON BROADCASTING, Vol. 56, No. 3, September 2010
[14] 劉楷哲,吳其霖, "基於3D顯示器格式之即時3D內容合成技術", 工業技術研究院 電子與光電研究所,影像與識別2010, Vol. 16 No. 2
[15] Y.M. Feng, DX Li, K Luo and M Zhang, "Asymmetric Bidirectional View Synthesis for Free Viewpoint and Three-Dimensional Video," IEEE Transactions on Consumer Electronics, Vol.55, no.4, pp.2349-2355, Nov. 2009.
[16] W.K. Giloi, J.L. Encarnação, W. Straßer. "The Giloi’s School of Computer Graphics". Computer Graphics 35 4:12–16
[17] Li Yu, Sen Xiang, Huiping Deng and Peng Zhou, "Depth based View Synthesis with Artifacts Removal for FTV", Image and Graphics (ICIG), pp. 506-510,12-15 Aug. 2011 "
[18] L. Azzari, F. Battisti, and A. Gotchev, "Comparative Analysis of oOcclusion-filling Techniques in Depth Image-based Rendering for 3D Videos " in Proc. 3rd Workshop Mobile Video Delivery, New York, 2010, pp.57–62, MoViD ’10.
[19] M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester, "Image inpainting", in Proc. ACM SIGGRAPH, Intern. Conf. on Computer Graphics and Interactive Techniques, 174, pp. 417–424, (New Orleans, LA), July 2000
[20] C. Vázquez, W. J. Tam, and F. Speranza, "Stereoscopic imaging: Filling disoccluded areas in depth image-based rendering", in Proc.Soc. Photo-Opt. Instrum. Eng. (SPIE) Conf. Series, Oct. 2006, Vol.6392.
[21] Lai-Man Po, Shihang Zhang, "A New Multidirectional Extrapolation Hole-Filling Method For Depth-Image-Based Rendering", Image Processing (ICIP) 18th IEEE International Conference, pp. 2589 – 2592, 11-14 Sept. 2011
[22] Yi-Hsiang Chiu and Jar-Ferr Yang, " GPU Implementation of Versatile Multiview DIBR Algorithms ", National Cheng Kung University, July 2012
[23] Steam 硬體 & 軟體調查 http://store.steampowered.com/hwsurvey
[24] OpenCL http://www.khronos.org/opencl/
[25] Heterogeneous System Architecture Foundation http://hsafoundation.com/
[26] Shahram Izadi, David Kim, Otmar Hilliges, David Molyneaux "KinectFusion: Real-time 3D Reconstruction and Interaction Using a Moving Depth Camera", Research conducted at Microsoft Research Cambridge, UK, 16-19 October. 2011
[27] Svitlana Zinger, Daniel Ruijters, Luat Do, and Peter H. N. de With, " View Interpolation for Medical Images on Autostereoscopic Displays", IEEE Transactions, Circuits and Systems for Video Technology, pp.128-137, Jan. 2012
[28] Titan - Cray XK7 , Opteron 6274 16C 2.200GHz, Cray Gemini interconnect, NVIDIA K20x, http://www.top500.org/
[29] NVIDIA, "GeForce_8800_GPU_Architecture_Technical_Brief", November 2006
[30] Microsoft Developer Network http://msdn.microsoft.com/en-US/
[31] Yi-Hsiang Chiu and Jar-Ferr Yang, "Efficient 3D Video Packing and Comfort Disparity Modification for Traditional Broadcasting Systems" , National Cheng Kung University, July 2013