文字藝術與文字雲，通常是指將文字以圖像的形式直觀地呈現，並且通過改變文字的字形大小與位置等方式強調文字的重要度差別。以往關於文字雲的電腦圖學研究，大多側重於圖像的形狀和外緣輪廓，專注於在平面上表現文字藝術化效果。而為了更好地表現圖像本來的細節，本篇論文考慮引入圖像的深度訊息作為依據，在2.5D模型表面呈現文字藝術效果。本篇論文基於一張具有透視立體效果的圖像，估計其深度訊息從而生成2.5D模型，以此作為輸入。我們通過模型參數化在二維平面上描述圖像的深度訊息，並且設計了一個交互系統讓使用者對文字塊作藝術化處理。同時利用一個眼動追蹤視覺模型分析觀賞者注意力在圖像上的分佈，引導使用者排列文字，在局部區域採用平面文字雲方法突出文字主體，並將文字依照模型的深度訊息做變形以表現立體感。最終生成貼圖呈現在模型上，產生強調原圖像局部細節、深度效果以及圖文內容的藝術作品。

Text visualization intuitively express a summary composited with graphic symbol, and word art composite with the size and position of font character to generate a stylized result. Previous work art in computer graphics focus on the 2D word art representation in a simple shape and boundary. We introduce a word art with detailed context by considering the depth of the input image. Given a 2.5D model by analyzing the depth information of input image. First, we use mesh parameterization to build a depth enhance texture coordinate. Second, we build an interactive system to assist user to design the word block. An eye tracking visual model is used to explore the attention distribution over an image to guide user to place the key word on most salient image. To render the word with depth enhance, we generate the word cloud in partial regions on the mesh parameterization. We demonstrate a word art with depth and context enhancement compared to several artist works.

[H15] Shi-Yang Huang. "Generating 3D Lenticular Effects from a Single Image" Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan, R.O.C., 2015
[CLC*15] Ming-Te Chi, Shih-Syun Lin, Shiang-Yi Chen, Chao-Hung Lin, and Tong-Yee Lee. "Morphable Word Clouds for Time-Varying Text Data Visualization." Visualization and Computer Graphics, IEEE Transactions on 21, no. 12 (2015): 1415-1426.
[MBS*11] Ron Maharik, Mikhail Bessmeltsev, Alla Sheffer, Ariel Shamir, and Nathan Carr. "Digital micrography." In ACM Transactions on Graphics (TOG), vol. 30, no. 4, p. 100. ACM, 2011.
[HLJ*14] Zhenzhen Hu, Si Liu, Jianguo Jiang, Richang Hong, Meng Wang, and Shuicheng Yan. "PicWords: Render a Picture by Packing Keywords."Multimedia, IEEE Transactions on 16, no. 4 (2014): 1156-1164.
[JED*09] Tilke Judd, Krista Ehinger, Frédo Durand, and Antonio Torralba. "Learning to predict where humans look." In Computer Vision, 2009 IEEE 12th international conference on, pp. 2106-2113. IEEE, 2009.
[GFL08] Laura Granka, Matthew Feusner, and Lori Lorigo. "Eye monitoring in online search." In Passive eye monitoring, pp. 347-372. Springer Berlin Heidelberg, 2008.
[BSI14] Ali Borji, Dicky N. Sihite, and Laurent Itti. "What/where to look next? Modeling top-down visual attention in complex interactive environments." Systems, Man, and Cybernetics: Systems, IEEE Transactions on 44, no. 5 (2014): 523-538.
[LPR*02] Bruno Lévy, Sylvain Petitjean, Nicolas Ray, and Jérome Maillot. "Least squares conformal maps for automatic texture atlas generation." In ACM Transactions on Graphics (TOG), vol. 21, no. 3, pp. 362-371. ACM, 2002.
[P99] John Platt. "Fast training of support vector machines using sequential minimal optimization." Advances in kernel methods—support vector learning 3 (1999).
[SF95] Eero P. Simoncelli, and William T. Freeman. "The steerable pyramid: A flexible architecture for multi-scale derivative computation." In icip, p. 3444. IEEE, 1995.
[OT01] Aude Oliva, and Antonio Torralba. "Modeling the shape of the scene: A holistic representation of the spatial envelope." International journal of computer vision 42, no. 3 (2001): 145-175.
[R99] Ruth Rosenholtz. "A simple saliency model predicts a number of motion popout phenomena." Vision research 39, no. 19 (1999): 3157-3163.
[IK00] Laurent Itti, and Christof Koch. "A saliency-based search mechanism for overt and covert shifts of visual attention." Vision research 40, no. 10 (2000): 1489-1506.
[VJ01] Paul Viola, and Michael Jones. "Robust real-time object detection."International Journal of Computer Vision 4 (2001): 51-52.
[FMR08] Pedro Felzenszwalb, David McAllester, and Deva Ramanan. "A discriminatively trained, multiscale, deformable part model." In Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, pp. 1-8. IEEE, 2008.