| 研究生: |
李國豪 Lee, Kuo-Hao |
|---|---|
| 論文名稱: |
深度與紋理一致性之多視角影像合成演算法 Multiview Synthesis Algorithms Based on Depth and Texture Consistency |
| 指導教授: |
楊家輝
Yang, Jar-Ferr (Kevin) |
| 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: | 2011 |
| 畢業學年度: | 99 |
| 語文別: | 中文 |
| 論文頁數: | 120 |
| 中文關鍵詞: | 三向濾波器 、立體視覺 、多視角影像 、基於深度繪圖 、影像修補 、擴散式合成 |
| 外文關鍵詞: | depth-image-based rendering (DIBR), diffusion method, image inpainting, multiview, stereo vision, trilateral filter |
| 相關次數: | 點閱:149 下載:2 |
| 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 |
三維電視廣播系統可能傳送方式為單視角影像(monoscopic image)和相對應的深度圖(depth map),接收端則需一套品質良好的基於深度繪圖(depth-image-based rendering,DIBR)系統產生多視角影像,不僅相容於既有二維內容、減少傳輸頻寬,傳輸內容也不受立體顯示器限制。
但由於單視角資訊不足,虛擬視角影像中常會有不自然的假影(artifacts)。本論文提出的深度與紋理一致性之多視角影像合成演算法,利用適應性三向濾波優化深度圖,再藉著可調式三維影像變形模擬最舒視差,並防止線型裂縫的產生。透過紋理與深度相互參照之影像修補技術填補影像空洞,最後利用擴散式合成法產生多視角影像,可大幅減少假影及幻像,改善虛擬影像的品質。經實驗證明,本研究可使立體影像對在各種立體顯示器上真實、自然地呈現,使觀者舒服地獲得深度感知。
The possible transmission format of future 3D Television broadcasting systems could be one monoscopic video plus its associated depth map. In this case, a high-quality depth-image-based rendering (DIBR) technique is desired at the receiver side to generate multiview images. The above systems will contain many advantages such as backward compatible with the traditional 2D digital TV system, low transmission bandwidth demand, and adaptability to different 3D displays.
Due to lack of information in the monoscopic video, there might occur some unnature artifacts in virtually-generated views. In this thesis, we propose multiview synthesis algorithms based on depth and texture consistency to reduce these artifacts and improve the quality of synthesized images. At first, the preprocessing is performed for the depth map with the proposed adaptive trilateral filter to preserve the sharp edges, correct the unmatched contours and remove the noises. And then we use the adjustable 3D image warping to prevent small cracks and fit the requirements for display devices. Furthermore, the proposed inpainting method is used to fill the large hole regions. Finally, we synthesize the multiview images with a diffusion method to achieve better 3D visualization. With the help of our algorithm, the simulations verify that the audiences can perceive depth comfortably and enter the real 3D world without eyestrain, confusion and loss of stereopsis.
[1] Riddhi Patel, "3-D TV Shipments to Soar 463 Percent to 23.4 Million Units in 2011," IHS iSuppli Market Intelligence, 3 May 2011, Retrieved 31 May 2011 from http://www.isuppli.com/Display-Materials-and-Systems/MarketWatch/Pages/3-D-TV-Shipments-to-Soar-463-Percent-to-23-4-Million-Units-in-2011.aspx
[2] 櫻井正二郎,「雙眼立體視覺─視獨立的歷程嗎?」。載於李江山等著,「視覺與認知:視覺知覺與視覺認知系統」。初版,頁184-208,台北市:遠流,1999。
[3] Daniel Minoli, "Analytical 3D Aspects of the Human Visual System," in "3D Television (3DTV) Technology, Systems, and Deployment: Rolling Out the Infrastructure for Next-Generation Entertainment," 1st ed., pp.55-73, Boca Raton: CRC Press, 2011.
[4] Gerd Waloszek, "Vision and Visual Disabilities – An Introduction," SAP User Experience, SAP AG, 28 Sept. 2010.
[5] S. Palmer, "Vision Science: Photons to Phenomenology," pp.209, MIT Press, Cambridge, Massachusetts, 1999.
[6] W. A. IJsselsteijn; P. J. H. Seuntiëns; L. M. J. Meesters, "State-of-the-Art in Human Factors and Quality Issues of Stereoscopic Broadcast Television," ATTEST Project, Deliverable 1, no.IST-2001-34396, Aug. 2002.
[7] Ian, "Stereoscopic Parallax," 3D Forums, 10 Aug. 2009. Retrieved 31 May 2011 from http://www.3d-forums.com/stereoscopic-parallax-t4.html
[8] Charles Wheatstone, "On Some Remarkable, and Hitherto Unobserved, Phenomena of Binocular Vision," Philosophical Transactions of the Royal Society of London, vol.128, pp.371-394, 1838.
[9] Marshall Brain, "3-D viewing," in "How 3-D Glasses Work," HowStuffWorks.com, Retrieved 31 May 2011 from http://science.howstuffworks.com/3-d-glasses2.htm
[10] Michael Halle, "Autostereoscopic Displays and Computer Graphics," ACM SIGGRAPH Computer Graphics, vol.31, no.2, pp.58-62, May 1997.
[11] Philips Electronics Nederland B.V., "42-inch 3D-Intelligent Display: User Manual," Philips 3D Solutions, 1 Apr. 2009, Retrieved 31 May 2011 from http://www.business-sites.philips.com/shared/assets/3dsolutions/downloads/42Inch3dDisplayUserManual.pdf
[12] 戴亞翔,「瞭解顯示器」。載於「TFT-LCD面板的驅動與設計」。初版,頁14-15,台北市:五南,2007。
[13] Bernard Mendiburu, "Cinematography Equipment," in "3D Movie Making: Stereoscopic Digital Cinema from Script to Screen," 1st ed., p.201, Boston: Focal Press, 2009.
[14] D. Scharstein; R. Szeliski, "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms," International Journal of Computer Vision (ICJV), vol.47, no.1-3, pp.7-42, Apr.-Jun. 2002.
[15] G. J. Iddan; G. Yahav, "3D Imaging in the Studio (and Elsewhere...)," Proceedings of SPIE Videometrics and Optical Methods for 3D Shape Measurements '01, vol.4298, pp.48-55, Jan. 2001.
[16] Richard Hartley; Andrew Zisserman, "Multiple View Geometry in Computer Vision," 2nd ed., Cambridge University Press, Cambridge, UK, 2004.
[17] An-Ti Chiang, "Image Segmentation for Depth Estimation of Single View Images," Master’s Thesis, Institute of Computer and Communication Engineering, National Cheng Kung University, Tainan, 2009.
[18] Hung-Ming Wang; Chun-Hao Huang; Jar-Ferr 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 2010), pp.3248-3251, 30 May 2010-2 Jun. 2010.
[19] Chun-Hao Huang, "Depth Map Interpolation from Existing Pairs of Keyframes and Depth Maps for 3D Video Generation," Master’s Thesis, Institute of Computer and Communication Engineering, National Cheng Kung University, Tainan, 2010.
[20] T. Okino; H. Murata; K. Taima; T. Iinuma; K. Oketani, "New Television with 2D/3D Image Conversion Technologies," Proceedings of SPIE, vol.2653, pp.96-103, 1996.
[21] Hung-Ming Wang; Yan-Hong Chen; Jar-Ferr Yang, "A Novel Matching Frame Selection Method for Stereoscopic Video Generation," 2009 IEEE International Conference on Multimedia and Expo (ICME 2009), pp.1174-1177, 28 Jun. 2009-3 Jul. 2009.
[22] Yan-Hong Chen, "Static Stereoscopic Video Generation Algorithms," Master’s Thesis, Institute of Computer and Communication Engineering, National Cheng Kung University, Tainan, 2008.
[23] C. 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, 2004.
[24] G. Alain; W. J. Tam; L. Zhang, "Improving Stereoscopic Image Quality of Pictures Generated from Depth Maps," Internal CRC report, April 2003.
[25] M. Schmeing; Xiaoyi Jiang, "Depth Image Based Rendering: A Faithful Approach for the Disocclusion Problem," 2010 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON 2010), pp.1-4, 7-9 Jun. 2010.
[26] Yamanoue, H.; Okui, M.; Okano, F., "Geometrical Analysis of Puppet-Theater and Cardboard Effects in Stereoscopic HDTV Images," IEEE Transactions on Circuits and Systems for Video Technology, vol.16, no.6, pp.744-752, Jun. 2006.
[27] Thibos, N., "Image Processing by the Human Eye," Proceedings of SPIE Visual Communications and Image Processing IV, 1989.
[28] Liang Zhang; Tam, W.J., "Stereoscopic Image Generation Based on Depth Images for 3D TV," IEEE Transactions on Broadcasting, vol.51, no.2, pp.191-199, Jun. 2005.
[29] Ying-Rung Horng; Yu-Cheng Tseng; Tian-Sheuan Chang, "Stereoscopic Images Generation with Directional Gaussian Filter," Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS 2010), pp.2650-2653, 30 May 2010-2 Jun. 2010.
[30] Wan-Yu Chen; Yu-Lin Chang; Shyh-Feng Lin; Li-Fu Ding; Liang-Gee Chen, "Efficient Depth Image Based Rendering with Edge Dependent Depth Filter and Interpolation," 2005 IEEE International Conference on Multimedia and Expo (ICME 2005), pp.1314-1317, 6-6 Jul. 2005.
[31] Daribo, I.; Tillier, C.; Pesquet-Popescu, B., "Distance Dependent Depth Filtering in 3D Warping for 3DTV," 2007 IEEE 9th Workshop on Multimedia Signal Processing (MMSP 2007), pp.312-315, 1-3 Oct. 2007.
[32] Tomasi, C.; Manduchi, R., "Bilateral Filtering for Gray and Color Images," 1998 Sixth International Conference on Computer Vision, pp.839-846, 4-7 Jan. 1998.
[33] Kwan-Jung Oh; Sehoon Yea; Vetro, A.; Yo-Sung Ho, "Depth Reconstruction Filter and Down/Up Sampling for Depth Coding in 3-D Video," IEEE Signal Processing Letters, vol.16, no.9, pp.747-750, Sept. 2009.
[34] Y. Mori; N. Fukushima; T. Yendo; T. Fujii; M. Tanimoto, "View Generation with 3D Warping Using Depth Information for FTV," Signal Processing: Image Communication, vol. 24, no.1-2, pp.65-72, Jan. 2009.
[35] Liang-Hao Wang; Xiao-Jun Huang; Ming Xi; Dong-Xiao Li; Ming Zhang, "An Asymmetric Edge Adaptive Filter for Depth Generation and Hole Filling in 3DTV," IEEE Transactions on Broadcasting, vol.56, no.3, pp.425-431, Sept. 2010.
[36] Georg Petschnigg; Richard Szeliski; Maneesh Agrawala; Michael Cohen; Hugues Hoppe; Kentaro Toyama, "Digital, Photography with Flash and No-Flash Image Pairs," ACM Transactions on Graphics (TOG), vol.23, no.3, Aug. 2004.
[37] Johannes Kopf; Michael F. Cohen; Dani Lischinski; Matt Uyttendaele, "Joint Bilateral Upsampling," ACM Transactions on Graphics (TOG), vol.26, no.3, Jul. 2007.
[38] Chia-Ming Cheng; Shu-Jyuan Lin; Shang-Hong Lai; Jinn-Cherng Yang, "Improved Novel View Synthesis from Depth Image with Large Baseline," 2008 19th International Conference on Pattern Recognition (ICPR 2008), pp.1-4, 8-11 Dec. 2008.
[39] Gangwal, O.P.; Berretty, R.-P., "Depth Map Post-Processing for 3D-TV," 2009 Digest of Technical Papers International Conference on Consumer Electronics (ICCE 2009), pp.1-2, 10-14 Jan. 2009.
[40] Xue Jiufei; Xi Ming; Li Dongxiao; Zhang Ming, "A New Virtual View Rendering Method Based on Depth Image," 2010 Asia-Pacific Conference on Wearable Computing Systems (APWCS 2010), pp.147-150, 17-18 Apr. 2010.
[41] Ned Greene; Michael Kass; Gavin Miller, "Hierarchical Z-buffer Visibility," SIGGRAPH '93 Proceedings of the 20th annual conference on Computer graphics and interactive techniques, pp.231-240, 1993.
[42] L. McMillan, "An Image-Based Approach to Three-Dimensional Computer Graphics," PhD Thesis, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA, 1997.
[43] R-P.M. Berretty; F.J. Peters; G.T.G. Volleberg, "Real Time Rendering for Multiview Autostereoscopic," Proceddings of SPIE Stereoscopic Displays and Virtual Reality Systems XIII, vol.6055, pp.208-219, 2006.
[44] G. Wolberg, "Digital Image Warping," IEEE Computer Society Press, Los Alamitos, CA, USA, 1990.
[45] S. Zinger; L. Do; P. H. N. de With, "Free-Viewpoint Depth Image-Based Rendering," Journal of Visual Communication and Image Representation, vol.21, no.5-6, pp.533-541, 2010.
[46] Ya-mei Feng; Dong-xiao Li; Kai Luo; Ming 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.
[47] Kuan-Yu Chen; Pei-Kuei Tsung; Pin-Chih Lin; Hsin-Jung Yang; Liang-Gee Chen, "Hybrid Motion/Depth-Oriented Inpainting For Virtual View Synthesis in Multiview Applications," 2010 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON 2010), pp.1-4, 7-9 Jun. 2010.
[48] R. C. Gonzalez; R. E. Woods, "Digital Image Processing," 3rd ed., Prentice Hall, Upper Saddle River, NJ, 2008.
[49] Pei-Kuei Tsung; Pin-Chih Lin; Li-Fu Ding; Shao-Yi Chien; Liang-Gee Chen, "Single Iteration View Interpolation for Multiview Video Applications," 2009 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON 2009), pp.1-4, 4-6 May 2009.
[50] J. Shade; S. Gortler; L. He; R. Szeliski, "Layered Depth Images," SIGGRAPH '98 Proceedings of the 25th annual conference on Computer graphics and interactive techniques, pp. 231-242, Jul. 1998.
[51] Liu Zhan-wei; An Ping; Liu Su-xing; Zhang Zhao-yang, "Arbitrary View Generation Based on DIBR," 2007 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS 2007), pp.168-171, 28 Nov. 2007-1 Dec. 2007.
[52] Shu-Jyuan Lin, "Spatio-Temporally Consistent Multi-View Video Synthesis for Autostereoscopic Display," Master’s Thesis, Department of Computer Science, National Tsing Hua University, Hsinchu, 2009.
[53] M. Tanimoto, "Overview of Free Viewpoint Television," Signal Processing: Image Communication, vol.21, no.6, pp.454-461, Jul. 2006.
[54] William R. Mark; Leonard McMillan; Gary Bishop, "Post-Rendering 3D Warping," Proceedings of the 1997 Symposium on Interactive 3D Graphics, pp.7-16, 27-30 Apr. 1997.
[55] Pei-Jun Lee; Effendi, "Nongeometric Distortion
Smoothing Approach for Depth Map Preprocessing," IEEE Transactions on Multimedia, vol.13, no.2, pp.246-254, Apr. 2011.
[56] Marcelo Bertalmio; Guillermo Sapiro; Vicent
Caselles; Coloma Ballester, "Image Inpainting," Proceedings of the 27th annual conference on Computer graphics and interactive techniques, pp.417-424, Jul. 2000.
[57] Criminisi, A.; Perez, P.; Toyama, K., "Object Removal by Exemplar-Based Inpainting," Proceedings of 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol.2, pp.II–721-II–728, vol.2, 18-20 Jun. 2003.
[58] K. Luo; D. X. Li; Y. M. Feng; M. Zhang, "Depth-Aided Inpainting for Disocclusion Restoration of Multi-View Images Using Depth-Image-Based Rendering," Jounal of Zhejiang University Science A, vol.10, pp.1738-1749, Dec. 2009.
[59] Daribo, I.; Pesquet-Popescu, B., "Depth-Aided Image Inpainting for Novel View Synthesis," 2010 IEEE International Workshop on Multimedia Signal Processing (MMSP 2010), pp.167-170, 4-6 Oct. 2010.
[60] Kwan-Jung Oh; Sehoon Yea; Yo-Sung Ho, "Hole Filling Method Using Depth Based In-Painting for View Synthesis in Free Viewpoint Television and 3-D Video," Picture Coding Symposium (PCS 2009), pp.1-4, 6-8 May 2009.
[61] 陳順宇、鄭碧娥,統計學。四版,台北:華泰,2004。
[62] S. Reichelt; R. Häussler; G. Fütterer; N. Leister, "Depth Cues in Human Visual Perception and Their Realization in 3D Displays," Proceedings of SPIE Conference, vol.7690, pp.76900B–1-76900B–12, 2010.
[63] L. Lipton, "StereoGraphics Developers’ Handbook," StereoGraphics Corporation, San Rafael, CA, 1997.
[64] Y.-Y. Yeh; L. D. Silverstein, "Limits of Fusion and Depth Judgement in Stereoscopic Color Displays," Human Factors, vol.32, no.1, pp.45-60, Feb. 1990.
[65] L. F. Hodges, "Tutorial: Time-Multiplexed Stereoscopic Computer Graphics," IEEE Computer Graphics and Applications, vol.12, no.2, pp.20-30, Mar. 1992.
[66] B. Froner; N. Holliman; S. Liversedge, "A Comparative Study of Fine Depth Perception on Two-View 3D Displays," Displays Journal, vol.29, no.5, pp.440-450, Dec. 2008.
[67] 行政院勞工委員會勞工安全衛生研究所,台灣地區勞工人體計測資料庫。台北:行政院勞工委員會勞工安全衛生研究所,2000。
[68] Philips Electronics Nederland B.V., "3D Interface Specifications: White Paper," Philips 3D Solutions, 8 Apr. 2009, Retrieved 31 May 2011 from http://www.business-sites.philips.com/shared/assets/3dsolutions/downloads/3DInterfaceWhitePaper.pdf
[69] Philips 3D Sample content, Retrieved 30 Apr. 2008 from http://www.wowvx.com