簡易檢索 / 詳目顯示

研究生: 邱彥誠
Yen-Chen Chiu
論文名稱: 風格化魚類3D 模型生成
A Study on Stylized 3D Model Generation of Fishes
指導教授: 戴文凱
Wen-Kai Tai
口試委員: 金台齡
Tai-Lin Chin
紀明德
Ming-Te Chi
學位類別: 碩士
Master
系所名稱: 電資學院 - 資訊工程系
Department of Computer Science and Information Engineering
論文出版年: 2023
畢業學年度: 111
語文別: 英文
論文頁數: 59
中文關鍵詞: 風格化魚類模型程序生成風格化非剛性註冊3D 建模形變
外文關鍵詞: stylized fish models, procedural generation, stylization, 3D modeling, morphing
相關次數: 點閱:319下載:13
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
  • 在動畫和電腦遊戲行業中,創建3D 模型,尤其是風格化模型,面臨著複雜性和多樣性的挑戰。本研究針對這個需求,提出了一種結合程序生成和風格化的方法,專注於魚類模型。我們的研究目標是協助藝術家以高效方式創建多樣且具有視覺吸引力的3D 奇幻風格魚類模型。傳統的手動設計風格化魚類模型耗時且具有挑戰性,難以滿足動畫、遊戲開發和藝術設計行業的需求。而我們提出的方法通過結合參數化網格生成和風格化,提供了一個靈活且高效的工具,可以生成各種風格化魚類模型。此外,我們還加入了非剛性註冊的技術,使得魚模型能夠添加配飾。以及透過形變技術將魚類模型與風格模型的特徵融合,增加視覺上的趣味性。我們的實驗結果表明,這種方法能夠生成視覺吸引力和多樣性兼具的風格化魚類模型。這個工具為藝術家提供了一個有效的3D 建模解決方案,讓他們能夠創造出各種吸引人的魚類模型,適用於各種應用場景。


    In the animation and computer game industries, the creation of 3D models,
    especially stylized ones, poses challenges in terms of complexity and
    diversity. Our work addresses the need for efficient 3D content creation
    by introducing a method that combines procedural generation and stylization
    for fish models. The importance of this work lies in its ability to assist
    artists in efficiently creating diverse and visually appealing 3D fish models
    with fantasy features. Traditional manual design of stylized fish models is
    time-consuming and challenging, making it difficult to meet the demands
    of animation, game development, and art design industries. The proposed
    method addresses this issue by offering a tool that combines parameterized
    mesh generation and stylization, resulting in a wide variety of stylized
    fish models. The method also introduces a garment registration technique
    to incorporate accessories, and a morphing technique to blend features on
    fish model, adding an additional level of visual interest. Experimental results
    demonstrate the effectiveness of the method in generating visually
    appealing and diverse stylized fish models. This tool provides artists with
    a flexible and efficient solution for 3D modeling, empowering them to create
    captivating fish models for various applications.

    Recommendation Letter . . . . . . . . . . . . . . . . . . . . . . . . i Approval Letter . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii Abstract in Chinese . . . . . . . . . . . . . . . . . . . . . . . . . . iii Abstract in English . . . . . . . . . . . . . . . . . . . . . . . . . . iv Acknowledgements . . . . . . . . . . . . . . . . . . . . . . . . . . v Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ix List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xi 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1 Background and Motivation . . . . . . . . . . . . . . . . 1 1.2 Research Goals . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 Overview of Our Method . . . . . . . . . . . . . . . . . . 3 1.4 Contributions . . . . . . . . . . . . . . . . . . . . . . . . 4 1.5 Organization of This Thesis . . . . . . . . . . . . . . . . . 5 2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.1 Stylization . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.2 Registration . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.3 Mesh Morphing . . . . . . . . . . . . . . . . . . . . . . . 9 3 Proposed Method . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.2 Registration . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.2.1 Preprocessing . . . . . . . . . . . . . . . . . . . . 15 3.2.2 Extended Coherent Point Drift . . . . . . . . . . . 17 3.2.3 Blendshape . . . . . . . . . . . . . . . . . . . . . 22 3.2.4 Experiment . . . . . . . . . . . . . . . . . . . . . 23 3.3 Morphing . . . . . . . . . . . . . . . . . . . . . . . . . . 24 3.3.1 Spherical Parameterization . . . . . . . . . . . . . 24 3.3.2 Correspondence Construction . . . . . . . . . . . 26 3.3.3 Surface Blending . . . . . . . . . . . . . . . . . . 27 4 Results and Discussion . . . . . . . . . . . . . . . . . . . . . . 30 4.1 Experiment Environment . . . . . . . . . . . . . . . . . . 30 4.2 Target Images and Inputs . . . . . . . . . . . . . . . . . . 30 4.3 Result Models . . . . . . . . . . . . . . . . . . . . . . . . 36 5 Conclusions and Future Work . . . . . . . . . . . . . . . . . . . 40 5.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . 40 5.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . 42 References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 Letter of Authority . . . . . . . . . . . . . . . . . . . . . . . . . . 47

    [Alexa, 1999] Alexa, M. (1999). Merging polyhedral shapes with scattered features. In Proceedings Shape
    Modeling International ’99. International Conference on Shape Modeling and Applications, pages 202–
    210.
    [Blanz and Vetter, 1999] Blanz, V. and Vetter, T. (1999). A morphable model for the synthesis of 3d faces.
    In Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH
    ’99, page 187–194, USA. ACM Press/Addison-Wesley Publishing Co.
    [Dima Sindyaev, 2015] Dima Sindyaev (2015). Fishies Slot. IOS.
    [Epic Games, 2012] Epic Games (2012). Sketchfab. https://sketchfab.com/. Retrieved May, 5, 2023.
    [Gameview Studios, 2011] Gameview Studios (2011). Tapfish. IOS, Android.
    [Gameview Studios, 2014] Gameview Studios (2014). Dream Fish. IOS.
    [Giant Squid, 2016] Giant Squid (2016). ABZU. Steam, PS4.
    [Golyanik et al., 2016] Golyanik, V., Taetz, B., Reis, G., and Stricker, D. (2016). Extended coherent point
    drift algorithm with correspondence priors and optimal subsampling. In 2016 IEEE Winter Conference
    on Applications of Computer Vision (WACV), pages 1–9.
    [Han et al., 2021] Han, F., Ye, S., He, M., Chai, M., and Liao, J. (2021). Exemplar-based 3d portrait
    stylization. IEEE Transactions on Visualization and Computer Graphics, pages 1–1.
    [Huang et al., 2018] Huang, Y.-J., Lin, W.-C., Yeh, I.-C., and Lee, T.-Y. (2018). Geometric and Textural
    Blending for 3D Model Stylization. IEEE Transactions on Visualization and Computer Graphics,
    24(2):1114–1126.
    [Ingley et al., 2015] Ingley, S. J., Asl, M. R., Wu, C., Cui, R., Gadelhak, M., Li, W., Zhang, J., Simpson,
    J., Hash, C., Butkowski, T., Veen, T., Johnson, J. B., Yan, W., and Rosenthal, G. G. (2015). anyfish
    2.0: An open-source software platform to generate and share animated fish models to study behavior.
    SoftwareX, 3-4:13–21.
    [Kenta-Tanaka et al., 2019] Kenta-Tanaka et al. (2019). Probreg. Github.
    [Ligang Network, 2016] Ligang Network (2016). Hello Fishing 捕魚來了. Android.
    [Ma et al., 2015] Ma, Y., Zheng, J., and Xie, J. (2015). Foldover-free mesh warping for constrained texture
    mapping. IEEE Transactions on Visualization and Computer Graphics, 21(3):375–388.
    [Michel et al., 2022] Michel, O., Bar-On, R., Liu, R., Benaim, S., and Hanocka, R. (2022). Text2mesh:
    Text-driven neural stylization for meshes. In 2022 IEEE/CVF Conference on Computer Vision and
    Pattern Recognition (CVPR), pages 13482–13492.
    [Myronenko and Song, 2010] Myronenko, A. and Song, X. (2010). Point set registration: Coherent point
    drift. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(12):2262–2275.
    [Myronenko et al., 2006] Myronenko, A., Song, X., and Carreira-Perpiñán, M. (2006). Non-rigid point
    set registration: Coherent point drift. In Schölkopf, B., Platt, J., and Hoffman, T., editors, Advances in
    Neural Information Processing Systems, volume 19. MIT Press.
    [Nintendo Entertainment, 2020] Nintendo Entertainment (2020). Animal Crossing: New Horizons.
    [Parus and Kolingerová, 2004] Parus, J. and Kolingerová, I. (2004). Morphing of meshes with attributes.
    In Spring conference on Computer graphics.
    [Playrix Games, 2008] Playrix Games (2008). Fishdom. Windows, MacOS, Android, IOS.
    [Ploumpis et al., 2020] Ploumpis, S., Ververas, E., Sullivan, E. O., Moschoglou, S., Wang, H., Pears, N.,
    Smith, W., Gecer, B., and Zafeiriou, S. (2020). Towards a complete 3d morphable model of the human
    head. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP:1–1.
    [Practica Capital, 2011] Practica Capital (2011). Cgtrader. https://www.cgtrader.com/. Retrieved May, 5,
    2023.
    [Preda and Preteux, 2002] Preda, M. and Preteux, F. (2002). Critic review on mpeg-4 face and body animation.
    In Proceedings. International Conference on Image Processing, volume 3, pages 505–508
    vol.3.
    [Radford et al., 2021] Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G.,
    Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I. (2021). Learning transferable visual
    models from natural language supervision. In Meila, M. and Zhang, T., editors, Proceedings of the
    38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning
    Research, pages 8748–8763. PMLR.
    [Shutterstock, 2000] Shutterstock (2000). Turbosquid. https://www.turbosquid.com/. Retrieved April, 29,
    2023.
    [Sun et al., 2023] Sun, S.-Y., Chiu, Y.-C., and Tai, W.-K. (2023). Procedural 3d fish model generation with
    trainable shapes and textures from single image. Unpublished manuscript.
    [Sun and Murata, 2020] Sun, Y. and Murata, N. (2020). Cafm: A 3d morphable model for animals. In
    2020 IEEE Winter Applications of Computer Vision Workshops (WACVW), pages 20–24.
    [Tamiya and Dobashi, 2019] Tamiya, M. and Dobashi, Y. (2019). An interactive system for modeling fish
    shapes. In 2019 International Conference on Cyberworlds (CW), pages 395–398.
    [Tancik et al., 2020] Tancik, M., Srinivasan, P., Mildenhall, B., Fridovich-Keil, S., Raghavan, N., Singhal,
    U., Ramamoorthi, R., Barron, J., and Ng, R. (2020). Fourier features let networks learn high frequency
    functions in low dimensional domains. volume 33, pages 7537–7547. Curran Associates, Inc.
    [Xie et al., 2018] Xie, W., Shen, L., Yang, M., and Jiang, J. (2018). Facial expression synthesis with direction
    field preservation based mesh deformation and lighting fitting based wrinkle mapping. 77(6):7565–
    7593.
    [Xu and Jung, 2021] Xu, Y. and Jung, C. (2021). Face 2d to 3d reconstruction network based on head
    pose and 3d facial landmarks. In 2021 International Conference on Visual Communications and Image
    Processing (VCIP), pages 1–5.
    [Zuffi et al., 2018] Zuffi, S., Kanazawa, A., and Black, M. J. (2018). Lions and tigers and bears: Capturing
    non-rigid, 3d, articulated shape from images. In 2018 IEEE/CVF Conference on Computer Vision and
    Pattern Recognition, pages 3955–3963.
    [Zuffi et al., 2017] Zuffi, S., Kanazawa, A., Jacobs, D. W., and Black, M. J. (2017). 3d menagerie: Modeling
    the 3d shape and pose of animals. In 2017 IEEE Conference on Computer Vision and Pattern
    Recognition (CVPR), pages 5524–5532.

    QR CODE