跳到主要內容

簡易檢索 / 詳目顯示

研究生: 劉維晉
Liu, Wei Ching
論文名稱: 使用可控制反應擴散之影像風格化技術
Controllable reaction diffusion for image stylization
指導教授: 紀明德
Chi, Ming Te
學位類別: 碩士
Master
系所名稱: 理學院 - 資訊科學系
論文出版年: 2014
畢業學年度: 102
語文別: 英文
論文頁數: 37
中文關鍵詞: 反應擴散影像風格化
外文關鍵詞: reaction diffusion, image stylization
相關次數: 點閱:231下載:30
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
  • 影像風格化是一種改變輸入影像的重要技術,其用來加強圖像的特徵並傳達視覺上的資訊,其中圖案的形狀與分布構成的風格化的基本要素。然而對於初學者而言,設計一個新的風格化圖案以及適當的分佈配置是不容易的。在本文中,提出了一個使用異向性反應擴散的圖像風格化以及圖案生成的方法,並從已知的反應擴散圖案為基礎做延伸,同時保有反應擴散的自我組織圖案的特性。為了能夠有效的控制圖案的生成,利用調整後的異向性擴散用來控制圖案的形狀並結合流場調整圖案的排列。圖案的大小、密度、方向以及風格化樣式可藉由閥值的調整以及顏色映射加以控制。最後本系統用來生成剪紙、風格化半色調影像以及流場的視覺化的結果以突顯本系統之特色。


    Image stylization is an essential technique to create the style of input images, enhance image features, and express visual cues. The shape and distribution of the primitive are essential elements in stylization. However, designing a new pattern or creating an appropriate distribution can be challenging for novice users. In this paper, an anisotropic reaction diffusion system for image stylization and pattern generation is proposed. This system starts from modify existed reaction diffusion formula, but keeps the behaviors of reaction diffusion: self-organized patterns, stable pattern generation and multiple styled pattern. To enable more effective control over pattern generation, the proposed method utilizes a set of modifications on anisotropic diffusion to control shape and introduces a flow field to guide pattern arrangement. The size, density, orientation, and pattern style can be controlled by thresholding and toon mapping. The proposed system was used to generate images in the paper-cut, stylized halftone, and flow visualization, and the results are presented to highlight the control factors of the proposed system.

    致謝 i
    摘要 ii
    Abstract iii
    Contents iv
    List of Figures vi
    List of Tables viii
    CHAPTER 1 Introduction 1
    CHAPTER 2 Related work 4
    2.1. Reaction diffusion 4
    2.2. Image stylization 6
    2.3. Flow field 7
    CHAPTER 3 Method 9
    3.1. Overview 9
    3.2. Reaction diffusion 10
    3.3. Pattern type and control function 11
    3.3.1. Scaling factor 12
    3.3.2. Anisotropic Diffusion 13
    3.3.3. Flow-guided diffusion 18
    3.3.4. Control parameters 18
    3.4. Post process 19
    3.4.1. Tone Preserving Thresholding 19
    3.4.2. Direction Preserving Toon mapping 21
    CHAPTER 4 Results 24
    4.1. Paper cutting art 24
    4.2. Styled halftone image 26
    4.3. Flow field visualization 30
    CHAPTER 5 Conclusions 34
    References 36

    Barla, P., Thollot, J., & Markosian, L. (2006). X-toon: an extended toon shader. Proceedings of the 4th international symposium on Non-photorealistic animation and rendering.
    Chi, M.-T., Lee, T.-Y., Qu, Y., & Wong, T.-T. (2008). Self-animating images: illusory motion using repeated asymmetric patterns. ACM Transactions on Graphics (TOG).
    Kang, H., Lee, S., & Chui, C. K. (2007). Coherent line drawing. Proceedings of the 5th international symposium on Non-photorealistic animation and rendering.
    Kang, H., Lee, S., & Chui, C. K. (2009). Flow-based image abstraction. Visualization and Computer Graphics, IEEE Transactions on, 15(1), 62-76.
    Kim, T., & Lin, M. (2007). Stable advection‐reaction‐diffusion with arbitrary anisotropy. Computer Animation and Virtual Worlds, 18(4‐5), 329-338.
    Kyprianidis, J. E., & Döllner, J. (2008). Image Abstraction by Structure Adaptive Filtering. Proc. EG UK Theory and Practice of Computer Graphics.
    Lee, H., Seo, S., Ryoo, S., & Yoon, K. (2010). Directional texture transfer. Proceedings of the 8th International Symposium on Non-Photorealistic Animation and Rendering.
    Li, Y., Bao, F., Zhang, E., Kobayashi, Y., & Wonka, P. (2011). Geometry synthesis on surfaces using field-guided shape grammars. Visualization and Computer Graphics, IEEE Transactions on, 17(2), 231-243.
    McGraw, T. (2008). Generalized reaction–diffusion textures. Computers & Graphics, 32(1), 82-92.
    Pearson, J. E. (1993). Complex patterns in a simple system. Science, 261(5118), 189-192.
    Pizer, S. M., Amburn, E. P., Austin, J. D., Cromartie, R., Geselowitz, A., Greer, T., . . . Zuiderveld, K. (1987). Adaptive histogram equalization and its variations. Computer vision, graphics, and image processing, 39(3), 355-368.
    Sanderson, A. R., Johnson, C. R., & Kirby, R. M. (2004). Display of vector fields using a reaction-diffusion model. Visualization, 2004. IEEE.
    Turing, A. (1952). The Chemical Basis of Morphogenesis. Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences, 237(641), 37-72.
    Turk, G. (1991). Generating textures on arbitrary surfaces using reaction-diffusion (Vol. 25): ACM Siggraph Computer Graphics.
    Witkin, A., & Kass, M. (1991). Reaction-diffusion textures. ACM Siggraph Computer Graphics, 25(4), 299-308.
    Xu, J., & Kaplan, C. S. (2008). Artistic thresholding. Proceedings of the 6th international symposium on Non-photorealistic animation and rendering.
    Xu, J., Kaplan, C. S., & Mi, X. (2007). Computer-generated papercutting. Computer Graphics and Applications, 2007. PG'07. 15th Pacific Conference on.
    Yao, C.-Y., Chi, M.-T., Lee, T.-Y., & Ju, T. (2012). Region-based line field design using harmonic functions. Visualization and Computer Graphics, IEEE Transactions on, 18(6), 902-913.

    QR CODE
    :::