簡易檢索 / 詳目顯示

回結果列表
研究生： 許耕榮
Hsu, Keng-Jung
論文名稱： 影像置中深度解封裝與深度影像生成之GPU實現
GPU Implementation for Centralized Texture Depth Depacking and Depth Image-based Rendering
指導教授： 楊家輝
Yang, Jar-Ferr
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電腦與通信工程研究所
Institute of Computer & Communication Engineering
論文出版年： 2017
畢業學年度： 105
語文別： 英文
論文頁數： 59
中文關鍵詞： 基於深度影像生成技術 、影像置中深度封裝 、多視角繪圖技術
外文關鍵詞： Depth image based rendering, CTDP formats, multi-view rendering
相關次數： 點閱：152  下載：6 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 在過去幾十年來，3D 影像已經是現今科技熱門的趨勢之一。其中用裸眼3D螢幕來觀看3D影像更是未來的發展的趨勢。然而，現在的電視廣播節目是無法支援多視角3D影像的廣播。這是因為現在電視廣播系統的頻寬沒有辦法傳輸不同格式的多視角3D影像。因此，我們利用基於深度影像生成技術(DIBR)，一個能夠將2D影像轉成3D影像的技術。此技術需要有一張彩圖和其相關的深度圖來產生不同視角的影像用於合成裸眼3D影像。影像置中深度封裝(CTDP)格式系統同時符合基於深度影像生成技術(DIBR)和現今電視廣播的要求。此CTDP格式所產生的彩圖與其相關的深度圖會有更佳的品質。本論文將提出一個基於利用CTDP格式來產生2D影像及多種3D影像的系統。本系統模擬的實驗結果顯示出本系統相較於其他的多視角3D影像技術有更好的品質。另外，本系統利用GPU來加速3D影像產生的程序來達到即時播放的效果。

    In recent years, the 3D technique has become an important trend in nowadays techniques. The 3D video in auto-stereoscopic displays become the trend in the future. However nowadays 2D television broadcasting system doesn’t supports the 3D video transform. It is limits by delivering bandwidth that not satisfy for 3D video transform. Therefore, we utilize the depth image-based rendering (DIBR) algorithm, which is a 2D to 3D image conversion technique. DIBR system requires at least a texture image and an associated depth image to generate synthesized autostereoscopic 3D images. The centralized texture depth packing (CTDP formats are satisfy the DIBR system and can deliver in 2D television broadcasting system. It also has better quality on obtains texture image and depth image. In this thesis, a system includes 2D and 3D video player is proposed, which can support the original 2D contents and support the 3D video for auto-stereoscopic displays by utilizing the CTDP formats. Simulations show that the proposed system has better performance on compare with other multi-view rendering systems. The proposed system uses the GPU to accelerate the 3D rendering process to reach real time performance.

    摘 要 I Abstract II Contents IV List of Tables VII List of Figures VIII Chapter 1 Introduction 1 1.1 Research Background 1 1.1.1 Stereoscopic Visualization 3 1.1.2 Classification of 3D Displays 4 1.1.2.1 Stereoscopic Displays 5 1.1.2.2 Auto-stereoscopic Displays 8 1.2 Motivations 11 1.3 Thesis Organization 13 Chapter 2 Related Work 14 2.1 General Purpose GPU 14 2.1.1 Compute Unified Device Architecture (CUDA) 15 2.2 Depth Image-based Rendering 17 2.2.1 Preprocessing 17 2.2.2 Warping 18 2.2.3 Hole Filling 21 2.3 Centralized Texture Depth Packing Formats (CTDP) 22 Chapter 3 Proposed System and Algorithms 28 3.1 Overview of the Proposed System 28 3.2. Centralized Texture Depth Depacking 32 3.3 Directional Depth Image-based Rendering 34 3.3.1 Pre-processing of Depth Map 34 3.3.2 3D Warping 38 3.3.3 Directional Dependent-based Hole Filling 39 Chapter 4 GPU Implementation and Experimental Results 43 4.1 Analysis with Resize Methods of the CTDP Depacking 45 4.2 Analysis with Preprocessing Methods of the Synthesis View 48 4.3 Simulation Results of Synthesis Views 49 Chapter 5 Conclusions 53 Chapter 6 Future Work 54 References 55

    [1] Y.S. Izmantoko, A.B. Suksmono, and T.L. Mengko, “Implementation of anaglyph method for stereo microscope image display,” Proc. of International Conference on Electrical Engineering and Informatics, pp. 1–6, Jul. 2011.
    [2] S. Kejian, and W. Fei, “The development of stereoscopic display technology,” Proc. of 2010 3rd International Conference on Advanced Computer Theory and Engineering (ICACTE), vol.4, pp. 276–280, Aug. 2010.I. Sexton, “Parallax Barrier 3-D TV,” Proc. of SPIE, vol. 1083, pp. 84, 1989.
    [3] H. J. Lee, H. Nam, and J. D. Lee, “A high resolution autostereoscopic display employing a time division parallax barrier,” in SID Symposium Digest of Technical Papers, vol. 37, pp. 81–84, Jun. 2006. “Dolby Open Specification for Frame-compatible 3D Systems,” Dolby Laboratories, Inc.: http://www.dolby.com/
    [4] T. Kanade and M. Okutomi, “A Stereo Matching Algorithm with and Adaptive Window: Theory and Experiment,” IEEE Transaction on Pattern Analysis and Matching Intelligence, vol. 16, no. 9, pp.920-932, Sept. 1994.
    [5] K. Zhang, J. Lu, and G. Lafruit, “Cross-based Local Stereo Matching Using Orthogonal Integral Images,” IEEE Transaction on Circuits and Systems for Video Technology, vol. 19, no. 7, pp.1073-1079, July 2009.
    [6] S.-C. Chan, H.-Y. Shum, and K.-T. Ng, “Image-based Rendering and Synthesis,” IEEE Signal Processing Magazine, vol. 24, no. 6, pp. 22–33, Nov. 2007.
    [7] T.-C. Yang, P.-C. Kuo, B.-D. Liu, and J.-F. Yang, “Depth Image-based Rendering with Edge-oriented Hole Filling for Multiview Synthesis,” Proc. of International Conference of Communications, Circuits, and Systems, vol. 1, pp. 50-53, June 2013.
    [8] J.-F. Yang, K.-Y. Liao, H.-M. Wang and Y.-H. Hu, “Centralized Texture-Depth Packing (CTDP) SEI Message Syntax,” Joint Collaborative Team on 3D Video Coding Extensions of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29/WG 11, Document no. JCT3V-J0108, Strasbourg, Oct. 2014.
    [9] J.-F. Yang, K.-Y. Liao, H.-M. Wang, and C.-Y. Chen, “Centralized Texture-Depth Packing (CTDP) SEI Message,” Joint Collaborative Team on 3D Video Coding Extensions of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29/WG 11, the 11th Meeting: Document: JCT3V-K0027, Geneva, CH, Feb. 2015.
    [10] J.-F. Yang, H.-M. Wang, and C.-Y. Chen, “Revised Centralized Texture-Depth Packing (CTDP) SEI Message and Its Performance Improvement by Depth Enhancement,” Joint Collaborative Team on 3D Video Coding Extensions of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29/WG 11, the 12th Meeting: Document: JCT3V-L0022, Warsaw, PL, June. 2015.
    [11] J.-F. Yang, H.-M. Wang, and C.-Y. Chen, “Centralized Texture-Depth Packing SEI Message for HEVC,” Joint Collaborative Team on 3D Video Coding Extensions of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29/WG 11, the 13th Meeting: Document: JCT3V-M0022, Geneva, CH, Oct. 2015.
    [12] J.-V. Team, “Advanced Video Coding for Generic Audio-visual Services,” ITU-T Rec. H 264, 14496-10. 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 2004.
    [13] L. Zhang and W. J. Tam, “Stereoscopic image generation based on depth images for 3D TV,” IEEE Trans. on Broadcast, vol. 51, no. 2, pp. 191–199, Jun. 2005.
    [14] W. J. Tam, G. Alain, L. Zhang, T. Martin, and R. Renaud, “Smoothing depth maps for improved stereoscopic image quality,” Proc. of SPIE, vol. 5599, pp.162–172, Oct. 2004.
    [15] L.H. Wang and X.J. Huang, “An asymmetric edge adaptive filter for depth generation and hole filling in 3DTV,” IEEE Transactions on Broadcasting, vol. 56, no. 3, pp. 425–431, Sep. 2010.
    [16] P. J. Lee and Effendi, “Nongeometric distortion smoothing approach for depth map preprocessing,” IEEE Transactions on Multimedia, vol. 13, no. 2, pp. 246–254, Apr. 2011.
    [17] 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, vol. 16 no. 2, 2010.
    [18] 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.
    [19] L. Zhang, W. J. Tam, and D. Wang, “Stereoscopic image generation based on depth images,” Proc. of IEEE International Conference on Image Processing, vol. 5, pp. 2993–2996, Oct. 2004.
    [20] L. Azzari, F. Battisti, and A. Gotchev, “Comparative analysis of occlusion-filling techniques in depth image-based rendering for 3D videos,” Proc. of 3rd Workshop Mobile Video Delivery, pp.57–62, 2010.
    [21] M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester, “Image inpainting,” ACM SIGGRAPH, Proc. of Intern. Conf. on Computer Graphics and Interactive Techniques, pp. 417–424, Jul. 2000.
    [22] C. Vázquez, W. J. Tam, and F. Speranza, “Stereoscopic imaging: Filling disoccluded areas in depth image-based rendering,” in Proc. of Soc. Photo-Opt. Instrum. Eng. (SPIE) Conf. Series, vol. 6392, Oct. 2006.
    [23] A. Criminisi, P. Perez, and K. Toyama, “Region filling and object removal by exemplar-based image inpainting,” IEEE Trans. on Image Process., vol. 13, no. 9, pp. 1200–1212, Sep. 2004.
    [24] Daribo, Ismaël, and P. -P. Béatrice "Depth-aided image inpainting for novel view synthesis." Multimedia Signal Processing (MMSP), International Workshop on. IEEE, 2010.
    [25] Ahn, Ilkoo, and C. Kim. "A novel depth-based virtual view synthesis method for free viewpoint video." IEEE Transactions on Broadcasting, vol. 59, no. 4, pp. 614-626, 2013.
    [26] R. G. Keys, “Cubic Convolution Interpolation for Digital Image Processing,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 29, pp. 1153-1160, Dec. 1981.
    [27] Mohler, R. Ronald Bilinear control processes: with applications to engineering, ecology and medicine. Academic Press, Inc., 1973.
    [28] E. Angel and A. Jain, “A Nearest Neighbors Approach to Multidmnsional Filtering,” Proc. of IEEE Conference. on Decision and Control, pp. 84-88, Dec. 1972.
    [29] Duchon, C. E. "Lanczos Filtering in One and Two Dimensions." Journal of Applied Meteorology 18.8 (1979): 1016-1022.
    [30] S. Il Lee, Y. J. Jung, H. Sohn, F. Speranza, and Y. M. Ro, “Effect of stimulus width on the perceived visual discomfort in viewing stereoscopic 3DTV,” IEEE Trans. on Broadcasting, vol. 59, no. 4, pp. 580–590, 2013.
    [31] L. Azzari, F. Battisti, and A. Gotchev, “Comparative analysis of occlusion-filling techniques in depth image-based rendering for 3D videos,” Proc. of 3rd Workshop Mobile Video Delivery, pp.57–62, 2010.
    [32] M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester, “Image inpainting,” ACM SIGGRAPH, Proc. of Intern. Conf. on Computer Graphics and Interactive Techniques, pp. 417–424, 2000.
    [33] De Silva, D. V. SX, W. A. C. Fernando, and H. K. Arachchi. "A new mode selection technique for coding depth maps of 3D video." Proc. of IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2010.
    [34] Daribo, Ismaël, and H. Saito. "A novel inpainting-based layered depth video for 3DTV." IEEE Transactions on Broadcasting, vol. 57, no. 2, pp. 533–541, 2011.

    下載圖示 校內：2022-07-17公開
    校外：2022-07-17公開
    QR CODE