簡易檢索 / 詳目顯示

研究生: 李俊陞
論文名稱: 具低資料傳輸率之向量式臉部動畫合成法
A low data rate vector-based facial animation
指導教授: 楊熙年
口試委員:
學位類別: 碩士
Master
系所名稱: 電機資訊學院 - 資訊系統與應用研究所
Institute of Information Systems and Applications
論文出版年: 2005
畢業學年度: 93
語文別: 英文
論文頁數: 35
中文關鍵詞: 向量式臉部動畫合成低傳輸率
相關次數: 點閱:2下載:0
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
  • 我們展示了一個新的架構,可以利用影片或Mocap資料產生二維線條化的動畫,從這兩種資料中得到臉部表情的變化,進而產生臉部動畫。我們用SVG產生一個model,使得得到的資料可以在這個model上產生相對應的臉部動畫,由於向量式的圖形相當省空間,而且也有相當好的品質,所以利用SVG做出來的動畫,可以有相當好的成果。


    TABLE OF CONTENTS ACKNOWLEDGEMENTS . . . . . . . . . . . . . . . . . . . . . . . . . . iii LIST OF TABLES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi LIST OF FIGURES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vii SUMMARY . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . viii I INTRODUCTION . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 II RELATED WORK . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.1 Facial Modelling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.1.1 Non-photorealistic . . . . . . . . . . . . . . . . . . . . . . . . 6 2.2 Facial Animation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.2.1 Performance driven . . . . . . . . . . . . . . . . . . . . . . . 7 2.2.2 Physical based (Muscle based) . . . . . . . . . . . . . . . . . 9 2.2.3 Expression Cloning . . . . . . . . . . . . . . . . . . . . . . . 10 2.2.4 Data driven (Motion data) . . . . . . . . . . . . . . . . . . . 11 2.2.5 MPEG-4 FAPs . . . . . . . . . . . . . . . . . . . . . . . . . 11 III DATA DRIVEN FACIAL ANIMATION . . . . . . . . . . . . . . . 12 3.1 Deformable model preparation . . . . . . . . . . . . . . . . . . . . . 12 3.1.1 SVG model . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.2 Animation Sources . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.2.1 Video . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.2.2 MPEG-4 FAPs . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.2.3 Mocap . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 3.3 Mapping Function . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 3.3.1 Video . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 3.3.2 MPEG-4 FAPs . . . . . . . . . . . . . . . . . . . . . . . . . 20 iv 3.3.3 MOCAP . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 IV EXPERIMENTAL RESULT . . . . . . . . . . . . . . . . . . . . . . 22 V CONCLUSION . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 APPENDIX A — 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 REFERENCES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 v LIST OF TABLES 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 2 The comparison of file size in different file type and different video sequences . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 3 The depicted FAP definitions, group assignments, and step sizes. . . 27 vi LIST OF FIGURES 1 An example showing the suggestive contours . . . . . . . . . . . . . . 3 2 The framework of this paper . . . . . . . . . . . . . . . . . . . . . . 4 3 An illustration of Hong Chen’s system . . . . . . . . . . . . . . . . . 7 4 Illustration of speech-driven facial expression . . . . . . . . . . . . . 8 5 Illustration of simple muscle model . . . . . . . . . . . . . . . . . . . 9 6 Illustration of complex muscle model . . . . . . . . . . . . . . . . . . 10 7 Facial motion capture . . . . . . . . . . . . . . . . . . . . . . . . . . 11 8 The SVG facial model: Mulan . . . . . . . . . . . . . . . . . . . . . . 13 9 Amount of training data is not positive corelation to tracking result. The red line use 100 training data, the blue line use 91 training data 15 10 Result of tracking face . . . . . . . . . . . . . . . . . . . . . . . . . . 16 11 The result of using my facial expression record to produce FAPs and transform to facial animation . . . . . . . . . . . . . . . . . . . . . . 22 12 The result of using mocap data to transform to facial animation . . 23 13 Slides of the three kinds of videos in the comparison table . . . . . . 24 14 The illustration of dipicted FDP feature points . . . . . . . . . . . . 26

    [1] Alexa, M., Cohen-Or, D., and Levin, D., “As-rigid-as-possible shape interpolation,”
    in Proceedings of the 27th annual conference on Computer graphics
    and interactive techniques, pp. 157–164, ACM Press/Addison-Wesley Publishing
    Co., 2000.
    [2] Barshatzky, K. and Kerrigan, M., SVG and SMIL for Interactive Multimedia
    Documents. ACM SIGGRAPH Course Note 37, 2003.
    [3] Bregler, C., Covell, M., and Slaney, M., “Video rewrite: driving visual
    speech with audio,” in Proceedings of the 24th annual conference on Computer
    graphics and interactive techniques, pp. 353–360, ACM Press/Addison-Wesley
    Publishing Co., 1997.
    [4] Buck, I., Finkelstein, A., Jacobs, C., Klein, A., Salesin, D. H., Seims,
    J., Szeliski, R., and Toyama, K., “Performance-driven hand-drawn animation,”
    in NPAR 2000 : First International Symposium on Non-Photorealistic
    Animation and Rendering, pp. 101–108, June 2000.
    [5] Burford, D. and Blake, E., “Face-to-face implies no interface,” in 2nd South
    African Conference on Human-Computer Interaction, (Pretoria, South Africa),
    University of Pretoria, 2001.
    [6] Cani, M.-P. and Hornus, S., “Subdivision-curve primitives: A new solution
    for interactive implicit modeling,” in Proceedings of the International Conference
    on Shape Modeling & Applications, p. 82, IEEE Computer Society, 2001.
    [7] Chen, H., Liu, Z., Rose, C., Xu, Y., Shum, H.-Y., and Salesin, D.,
    “Example-based composite sketching of human portraits,” in NPAR ’04: Proceedings
    of the 3rd international symposium on Non-photorealistic animation
    and rendering, (New York, NY, USA), pp. 95–153, ACM Press, 2004.
    [8] Choi, J. and Szymczak, A., “On coherent rotation angles for as-rigid-aspossible
    shape interpolation,” in Proceedings of the 15th Canadian Conference
    on Computational Geometry (CCCG), pp. 111–114, 2003.
    [9] DeCarlo, D., Finkelstein, A., Rusinkiewicz, S., and Santella, A.,
    “Suggestive contours for conveying shape,” ACM Trans. Graph., vol. 22, no. 3,
    pp. 848–855, 2003.
    32
    [10] Diepold, K., Grzeszczuk, R., Pandzic, I., Petajan, E., Sodagar, I.,
    Spierer, J., and Taubin, G., MPEG-4: The Next Generation for Interactive
    Media. ACM SIGGRAPH Course Note 11, 2002.
    [11] Ezzat, T., Geiger, G., and Poggio, T., “Trainable videorealistic speech
    animation,” ACM Transactions on Graphics, vol. 21, no. 3, pp. 388–398, 2002.
    [12] Finkelstein, A. and Salesin, D. H., “Multiresolution curves,” in Proceedings
    of the 21st annual conference on Computer graphics and interactive techniques,
    pp. 261–268, ACM Press, 1994.
    [13] Gleicher, M., “Retargetting motion to new characters,” in Proceedings of
    the 25th annual conference on Computer graphics and interactive techniques,
    pp. 33–42, ACM Press, 1998.
    [14] Hertzmann, A., Oliver, N., Curless, B., and Seitz, S. M., “Curve analogies,”
    in Proceedings of the 13th Eurographics workshop on Rendering, pp. 233–
    246, Eurographics Association, 2002.
    [15] Hornus, S., Angelidis, A., and Cani, M.-P., “Implicit modelling using
    subdivision-curves,” The Visual Computer, vol. 19, pp. 94–104, May 2003.
    [16] Kähler, K., Haber, J., Yamauchi, H., and Seidel, H.-P., “Head
    shop: generating animated head models with anatomical structure,” in SCA
    ’02: Proceedings of the 2002 ACM SIGGRAPH/Eurographics symposium on
    Computer animation, (New York, NY, USA), pp. 55–63, ACM Press, 2002.
    [17] K¨ahler, K., Haber, J., and Seidel, H.-P., “Reanimating the dead: reconstruction
    of expressive faces from skull data,” ACM Transactions on Graphics,
    vol. 22, no. 3, pp. 554–561, 2003.
    [18] Koch, R. M., Gross, M. H., Carls, F. R., von Büren, D. F.,
    Fankhauser, G., and Parish, Y. I. H., “Simulating facial surgery using
    finite element models,” in SIGGRAPH ’96: Proceedings of the 23rd annual
    conference on Computer graphics and interactive techniques, (New York, NY,
    USA), pp. 421–428, ACM Press, 1996.
    [19] Kurlander, D., Skelly, T., and Salesin, D., “Comic chat,” in Proceedings
    of the 23rd annual conference on Computer graphics and interactive techniques,
    pp. 225–236, ACM Press, 1996.
    [20] Lee, Y., Terzopoulos, D., and Walters, K., “Realistic modeling for facial
    animation,” in Proceedings of the 22nd annual conference on Computer graphics
    and interactive techniques, pp. 55–62, ACM Press, 1995.
    33
    [21] Lewis, J. P., Cordner, M., and Fong, N., “Pose space deformation: a
    unified approach to shape interpolation and skeleton-driven deformation,” in
    Proceedings of the 27th annual conference on Computer graphics and interactive
    techniques, pp. 165–172, ACM Press/Addison-Wesley Publishing Co., 2000.
    [22] Litwinowicz, P. and Williams, L., “Animating images with drawings,” in
    SIGGRAPH ’94: Proceedings of the 21st annual conference on Computer graphics
    and interactive techniques, (New York, NY, USA), pp. 409–412, ACM Press,
    1994.
    [23] Liu, Z., Shan, Y., and Zhang, Z., “Expressive expression mapping with ratio
    images,” in Proceedings of the 28th annual conference on Computer graphics
    and interactive techniques, pp. 271–276, ACM Press, 2001.
    [24] MobileSVG, W3C SVG Tiny Specification. World Wide Web Consortium
    (W3C): http://www.w3.org/TR/SVGMobile/, 2003.
    [25] Na, K. and Jung, M., “Hierarchical retargeting of fine facial motions,” in
    Computer Graphics Forum, vol. 23, Eurographics Association, 2004.
    [26] Noh, J. Y. and Neumann, U., “Expression cloning,” in Proceedings of the 28th
    annual conference on Computer graphics and interactive techniques, pp. 277–
    288, ACM Press, 2001.
    [27] Pandzic, I. S., “Facial motion cloning,” Graphical Models, vol. 65, no. 6,
    pp. 385–404, 2003.
    [28] Pandzic, I. S. and Forchheimer, R., eds., MPEG-4 Facial Animation - The
    standard, implementations and applications. John Wiley & Sons, 2002.
    [29] Pearson, D. E. and Robinson, J. A., “Visual communication at vrey low
    data rates,” in Proceedings of the IEEE, pp. 795–812, New York.Institute of
    Electrical and Electronics Engineers,1913-, 1985.
    [30] PocketSVG, PocketSVG. http://www.pocketsvg.com/, 2003.
    [31] Pyun, H., Kim, Y., Chae, W., Kang, H. W., and Shin, S. Y., “An examplebased
    approach for facial expression cloning,” in Proceedings of the 2003 ACM
    SIGGRAPH/Eurographics Symposium on Computer Animation, pp. 167–176,
    Eurographics Association, 2003.
    [32] Seitz, S. M. and Dyer, C. R., “View morphing,” in Proceedings of the 23rd
    annual conference on Computer graphics and interactive techniques, pp. 21–30,
    ACM Press, 1996.
    [33] Stegmann, M. B., The AAM-API. Richard Petersens Plads, Building 321,
    DK-2800 Kgs. Lyngby: Informatics and Mathematical Modelling, Technical
    University of Denmark, DTU, 2003. http://www.imm.dtu.dk/~aam/aamapi/.
    34
    [34] Stegmann, M. B., Fisker, R., Ersbøll, B. K., Thodberg, H. H., and
    Hyldstrup, L., “Active appearance models: Theory and cases,” in Proc. 9th
    Danish Conference on Pattern Recognition and Image Analysis (Johansen,
    P., ed.), vol. 1, (Aalborg, Denmark), pp. 49–57, AUC, 2000.
    [35] Waters, K., “A muscle model for animation three-dimensional facial expression,”
    in Proceedings of the 14th annual conference on Computer graphics and
    interactive techniques, pp. 17–24, ACM Press, 1987.
    [36] Williams, L., “Performance-driven facial animation,” in Proceedings of the
    17th annual conference on Computer graphics and interactive techniques,
    pp. 235–242, ACM Press, 1990.

    無法下載圖示 全文公開日期 本全文未授權公開 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)
    全文公開日期 本全文未授權公開 (國家圖書館:臺灣博碩士論文系統)
    QR CODE