萃取物體的曲線骨架是電腦圖學領域中一門重要的課題，由於傳統的萃取技術通常會利用到物體的立體像素化，
因此，萃取出的骨架不但會容易地受到立體像素化之解析度的影響並且需要使用到龐大的計算量。
我們提出一個全新的骨架萃取演算法，其是對物體表面做拉普拉斯平滑化以及簡單的物體簡化，我們也證明了提出
的演算法能有效率地萃取出各種物體的曲線骨架。

模型內插的應用亦與骨架有密切的相關性，模型內插的目的在於為兩個或多個模型之間產生一組自然且平順的幾何轉變。
然而當模型之間的姿勢差異量太大時，以表面為基礎的傳統幾何轉換演算法往往會造成嚴重的形變。
透過研究、觀察，我們發現，姿勢差異的問題可以藉由模型內部的鏈接結構來解決。
因此，我們提出一個多重解析度平均數位移分群演算法，用來全自動分析多個輸入模型並萃取出其代表性的鏈接結構。
藉由鏈接結構的輔助，我們可以從姿勢差異大的任何模型中得到令人滿意的內插結果。

人類視覺感知泛指人類大腦如何解讀眼睛所接收的資訊，而所謂的光學錯覺則是代表人腦錯誤解讀資訊的一種
有趣的現象。
一直以來，認知心理學家致力於研究具有光學錯覺的影像並提出各種理論來解釋人類的視覺感知的運作方式。
然而，大多數的光學錯覺影像是由藝術家透過手工繪製，數量的限制更侷限了視覺感知研究的範疇。
有鑑於此，近十年來，電腦圖學興起一股用計算模型去產生大量及特定的光學錯覺影像的熱潮。
本論文最後，我們提出了兩個系統雛型用來大量產生兩種知名的光學錯覺影像，浮現影像以及偽裝影像。

浮現影像的基礎原理為完形心理學，它描述了人類視覺如何將零散無意義的區塊組織成一個有意義的整體。
以完形心理學為基礎，我們提出演算法將任意的三維模型繪製成浮現影像並可控制人類感知浮現模型的難易程度。
此外，浮現影像技術亦提供一個嶄新的網路安全機制，稱做為CAPTCHA，用來全自動區分人類與間諜機器人。

偽裝影像的表現方式為將一個或多個物體隱藏在一張背景圖中，第一次觀看影像時，人類無法立即查覺隱藏的物體，
唯有透過集中注意力方能感受到隱藏的物體。
這樣的觀察方式，可以將人類視覺感知分為兩個基本步驟:特徵搜尋及關聯搜尋，透過抑制特徵搜詢，觀察者被迫
使用需要集中視覺注意力的關聯搜尋，基於以上準則，我們提出的技術便能將一般人或動物的照片隱藏在自然風景照片中
並且透過簡單的參數控制辨識隱藏物體的難易度。

Curve-Skeleton extraction is a fundamental problem in computer graphics and visualization.
It represents a simplified version of the geometry and topology of a 3D model.
Most existing skeleton extraction methods require a volumetric representation of the 3D
model which is highly dependent on the resolution of sampling grids and also expensive in
computation.
We propose a novel skeleton extraction method based on iterative Laplacian smoothing
with global positional constraints and a shape-aware mesh simplification.
Our method works directly on the mesh surface and efficiently extract skeleton within few
seconds.
We demonstrate the robustness of the method with several nice extracted curve-skeletons.

Shape interpolation, a gradually and naturally changing of transformation between
two or more existing shapes, also benefits from the skeleton structure.
When dealing with shape interpolation with significant pose variation, a naive
surface-based interpolation will generate serious artifacts.
The key for achieving a natural interpolation of articulated shapes is using underlying
skeleton to drive the path of interpolation.
We propose a multi-resolution mean-shift clustering algorithm to automatically
analyze and extract an articulated structure from a set of input shapes.
As a result, an aesthetically pleasing shape interpolation can be generated, with
even the poses of shapes varying significantly.

Human visual perception, also refereed to as human visual system (HSV), is the ability
of human brain to interpret information and surroundings from visible light reaching the eye.
Optical illusions, a phenomena that our HSV misinterprets the information from its physical
reality, are fascinating to look at and have been extensively studied in order to interpret
the workings of HSV.
We develop two prototype systems which aim at generating infinite number of images of two well-known
optical illusions, emergence and camouflage, to help on a better understand how HSV works.

Emergence is the phenomenon by which we perceive objects in an image not by recognizing the object
parts, but as a whole, all at once.
Motivated by Gestalt psychology, we present an automatic algorithm for creating emergence images
(and videos) of 3D objects (and animation) with controllable level of difficulty.
Such a synthesized image locally appear as noise, while revealing itself to a human observer when
viewed as a whole.
This holds potential for generating controlled test data for computer vision algorithms, as well
as creating puzzles to distinguish humans from bots, a potential internet security mechanism called Captcha.

Camouflage images contain one or more hidden figures that remain imperceptible or unnoticed
for a while.
In one possible explanation, the ability to delay the perception of the hidden figures is attributed
to the theory that human perception works in two main phases: feature search and conjunction search.
We present an algorithm for creating camouflage images from natural photos at controllable levels of
difficulty.
The proposed method mimics how skilled artists foil our feature search and leave clues for our
conjunction search.
Using our technique we generated a wide range of examples, with or without user guidance, and widely
tested the results with an extensive user study.

[1] A. Adams, N. Gelfand, J. Dolson, and M. Levoy. Gaussian kd-trees for fast high-dimensional filtering. ACM Trans. on Graphics (Proc. SIGGRAPH), 28(3):1-12, 2009.
[2] M. Alexa. Merging polyhedral shapes with scattered features. The Vis. Comp., 16(1):26-37, 2000.
[3] M. Alexa. Linear combination of transformations. ACM Trans. on Graphics, 21(3):380-387, 2002.
[4] M. Alexa. Differential coordinates for local mesh morphing and deformation. The Vis. Comp., 19(2-3):105-114, 2003.
[5] M. Alexa, D. Cohen-Or, and D. Levin. As-rigid-as-possible shape interpolation. In Proc. of ACM SIGGRAPH, pages 157-164, 2000.
[6] N. Amenta, S. Choi, and R. K. Kolluri. The power crust. In Symp. on Solid Modeling and Applications, pages 249-266, 2001.
[7] D. Anguelov, D. Koller, H.-C. Pang, P. Srinivasan, and S. Thrun. Recovering articulated object models from 3d range data. In Proc. of the Uncertainty in artificial intelligence, pages 18-26, 2004.
[8] D. Anguelov, P. Srinivasan, D. Koller, S. Thrun, J. Rodgers, and J. Davis. Scape: shape completion and animation of people. ACM Trans. on Graphics (Proc. SIGGRAPH), 24(3):408-416, 2005.
[9] G. Aujay, F. Hetroy, F. Lazarus, and C. Depraz. Harmonic skeleton for realistic character animation. In Symp. on Comp. Animation, pages 151-160, 2007.
[10] H. Barlow and S. P. Tripathy. Corresp. noise and signal pooling in the detection of coherent visual motion. J. Neurosci., 17(20), 1997.
[11] P. J. Besl and N. D. McKay. A method for registration of 3-d shapes. IEEE Trans. Pattern Anal. Mach. Intell., 14(2):239-256, 1992.
[12] I. Bitter, A. E. Kaufman, and M. Sato. Penalized-distance volumetric skeleton algorithm. IEEE Trans. on Vis. and Comp. Graphics, 7(3):195-206, 2001.
[13] M. Botsch, D. Bommes, and L. Kobbelt. Efficient linear system solvers for mesh processing. In Proc. of IMA on Mathematics of Surfaces, pages 62-83.
[14] M. Botsch, R. Sumner, M. Pauly, and M. Gross. Deformation transfer for detailpreserving surface editing. In Proc. of Vision, Modeling and Visualization, pages
357-364, 2006.
[15] Y. Boykov and V. Kolmogorov. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal.
Mach. Intell., 26(9):1124-1137, 2004.
[16] Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell., 23(11):1222-1239, 2001.
[17] E. Carmel and D. Cohen-Or. Warp-guided object-space morphing. The Vis. Comp., 13:465-478, 1997.
[18] P. Carr and R. Hartley. Solving multilabel graph cut problems with multilabel swap. Digital Image Computing: Techniques and Applications, 0:532-539, 2009.
[19] Y. Cheng. Mean shift, mode seeking, and clustering. IEEE Trans. Pattern Anal. Mach. Intell., 17(8):790-799, 1995.
[20] M.-T. Chi, T.-Y. Lee, Y. Qu, and T.-T. Wong. Self-animating images: Illusory motion using repeated asymmetric patterns. ACM Trans. on Graphics (Proc. SIGGRAPH), 27(3):62:1-62:8, 2008.
[21] J.-H. Chuang, C.-H. Tsai, and M.-C. Ko. Skeletonization of three-dimensional object using generalized potential field. IEEE Trans. Pattern Anal. Mach. Intell., 22(11):1241-1251, 2000.
[22] D. Cohen-Or, A. Solomovic, and D. Levin. Three-dimensional distance field metamorphosis. ACM Trans. on Graphics, 17(2):116-141, 1998.
[23] D. Comaniciu and P. Meer. Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell., 24(5):603-619, 2002.
[24] N. D. Cornea, P. Min, and D. Silver. Curve-skeleton properties, applications, and algorithms. IEEE Trans. on Vis. and Comp. Graphics, 13(3):530-548, 2007.
[25] N. D. Cornea, D. Silver, X. Yuan, and R. Balasubramanian. Computing hierarchical curve-skeletons of 3D objects. The Vis. Comp., 21(11):945-955, 2005.
[26] C. Cortes and V. Vapnik. Support vector networks. In Machine Learning, pages 273-297, 1995.
[27] K. G. Der, R. W. Sumner, and J. Popovic. Inverse kinematics for reduced deformable models. ACM Trans. on Graphics (Proc. SIGGRAPH), 25(3):1174-1179, 2006.
[28] M. Desbrun, M. Meyer, P. Schroder, and A. H. Barr. Implicit fairing of irregular meshes using di usion and curvature flow. In Proc. of ACM SIGGRAPH, pages 317-324, 1999.
[29] O. Deussen, S. Hiller, C. V. Overveld, and T. Strothotte. Floating points: A method for computing stipple drawings. Comp. Graphics Forum, 19:40-51, 2000.
[30] T. K. Dey and J. Sun. De ning and computing curve-skeletons with medial geodesic function. In Symp. on Geometry Processing, pages 143-152, 2006.
[31] A. A. Efros and W. T. Freeman. Image quilting for texture synthesis and transfer. In Proc. of ACM SIGGRAPH, pages 341-346, 2001.
[32] J. Elson, J. R. Douceur, J. Howel, and J. Saul. Asirra: a captcha that exploits interest-aligned manual image categorization. In ACM Conf. on CCS, pages 366-374, 2007.
[33] B. Epshtein and S. Ullman. Feature hierarchies for object classi cation. In IEEE ICCV, volume 1, pages 220-227, 2005.
[34] H. Fang and J. Hart. Textureshop: texture synthesis as a photograph editing tool. ACM Trans. on Graphics (Proc. SIGGRAPH), 23(3):354-359, 2004.
[35] R. Gal, O. Sorkine, T. Popa, A. Sheffer, and D. Cohen-Or. 3D collage: Expressive non-realistic modeling. In Proc. of NPAR, page 14. ACM, 2007.
[36] M. Garland and P. S. Heckbert. Surface simpli cation using quadric error metrics. In Proc. of ACM SIGGRAPH, pages 209-216, 1997.
[37] P. Golle. Machine learning attacks against the asirra captcha. In ACM Conf. on CCS, pages 535-542, 2008.
[38] M. S. Hassouna and A. A. Farag. Robust centerline extraction framework using level sets. In IEEE CVPR, pages 458-465, 2005.
[39] A. Hertzmann, C. E. Jacobs, N. Oliver, B. Curless, and D. H. Salesin. Image analogies. In Proc. of ACM SIGGRAPH, pages 327-340, 2001.
[40] M. Hilaga, Y. Shinagawa, T. Kohmura, and T. L. Kunii. Topology matching for fully automatic similarity estimation of 3D shapes. In ACM Trans. on Graphics (Proc. SIGGRAPH), pages 203-212, 2001.
[41] L. Huang and H. Pashler. A boolean map theory of visual attention. Psychological Review, 114:599-631, 2007.
[42] L. Huang, A. Treisman, and H. Pashler. Characterizing the limits of human visual awareness. Science, 317(5839):823, 2007.
[43] D. L. James and C. D. Twigg. Skinning mesh animations. In Proc. of ACM SIGGRAPH, pages 399-407, 2005.
[44] T. Kanai, H. Suzuki, and F. Kimura. Metamorphosis of arbitrary triangular meshes. IEEE Comput. Graph. Appl., 20(2):62-75, 2000.
[45] G. Kanizsa. Organization in Vision: Essays on Gestalt Perception. Praeger New York, 1979.
[46] C. S. Kaplan and D. H. Salesin. Escherization. In Proc. of ACM SIGGRAPH, pages 499-510, 2000.
[47] S. Katz, G. Leifman, and A. Tal. Mesh segmentation using feature point and core extraction. The Vis. Comp., 21(8{10):649-658, 2005.
[48] S. Katz and A. Tal. Hierarchical mesh decomposition using fuzzy clustering and cuts. In ACM Trans. on Graphics (Proc. SIGGRAPH), pages 954-961, 2003.
[49] M. Kilian, N. J. Mitra, and H. Pottmann. Geometric modeling in shape space. ACM Trans. on Graphics (Proc. SIGGRAPH), 26(3):64, 2007.
[50] B. Kim. Perceptual Org. for Arti cial Vision Sys. Springer, 2000.
[51] J. Kim and F. Pellacini. Jigsaw image mosaics. In Proc. of ACM SIGGRAPH, pages 657-664, 2002.
[52] V. Kolmogorov and R. Zabih. What energy functions can be minimized via graph cuts? In ECCV, pages 65-81, 2002.
[53] V. Kraevoy and A. Sheffer. Cross-parameterization and compatible remeshing of 3D models. In Proc. of ACM SIGGRAPH, pages 861-869, 2004.
[54] V. Kwatra, A. Schodl, I. Essa, G. Turk, and A. Bobick. Graphcut textures: image and video synthesis using graph cuts. ACM Trans. on Graphics (Proc. SIGGRAPH), 22(3):277-286, 2003.
[55] C. H. Lee, A. Varshney, and D. W. Jacobs. Mesh saliency. In Proc. of ACM SIGGRAPH, pages 659-666, 2005.
[56] T.-Y. Lee, Y.-S. Wang, and T.-G. Chen. Segmenting a deforming mesh into near-rigid components. The Vis. Comp., 22(9):729-739, 2006.
[57] X. Li, T.-W. Woon, T.-S. Tan, and Z. Huang. Decomposing polygon meshes for interactive applications. In Symp. on Interactive 3D Graphics, pages 35-42, 2001.
[58] Y. Lipman, O. Sorkine, D. Levin, and D. Cohen-Or. Linear rotation-invariant coordinates for meshes. ACM Trans. on Graphics, 24(3):479-487, 2005.
[59] A. Lobay and D. A. Forsyth. Shape from texture without boundaries. Int. Journal of Computer Vision, 67(1):71-91, 2006.
[60] D. G. Lowe. Distinctive image features from scale-invariant keypoints. Int. Journal of Computer Vision, 60:91-110, 2004.
[61] C.-M. Ma, S.-Y. Wan, and J.-D. Lee. Three-dimensional topology preserving reduction on the 4-sub elds. IEEE Trans. Pattern Anal. Mach. Intell., 24(12):1594-1605, 2002.
[62] W.-C. Ma, F.-C. Wu, and M. Ouhyoung. Skeleton extraction of 3D objects with radial basis functions. In Proc. of the Shape Modeling International, pages 207-215, 2003.
[63] C. Massot and J. Herault. Model of frequency analysis in the visual cortex and the shape from texture problem. Int. Journal of Computer Vision, 76(2):165-182, February 2008.
[64] N. J. Mitra. Personal communication (2009).
[65] N. J. Mitra and M. Pauly. Shadow art. ACM Trans. on Graphics (Proc. SIGGRAPH), 28(5):1-7, 2009.
[66] G. Mori and J. Malik. Recognizing objects in adversarial clutter: Breaking a visual captcha. In IEEE CVPR, pages 134-141, 2003.
[67] D. Nister and H. Stewenius. Scalable recognition with a vocabulary tree. In IEEE CVPR, pages 2161-2168, 2006.
[68] R. Ogniewicz and M. Ilg. Voronoi skeletons: Theory and applications. In IEEE CVPR, pages 63-69, 15-18 1992.
[69] A. Oliva, A. Torralba, and P. G. Schyns. Hybrid images. ACM Trans. on Graphics (Proc. SIGGRAPH), 25(3):527-532, 2006.
[70] J. Orchard and C. S. Kaplan. Cut-out image mosaics. In Proc. of NPAR, pages 79-87, 2008.
[71] V. Ostromoukhov, C. Donohue, and P.-M. Jodoin. Fast hierarchical importance sampling with blue noise properties. ACM Trans. on Graphics (Proc. SIGGRAPH), 23(3):488-495, 2004.
[72] K. Palagyi and A. Kuba. A parallel 3D 12-subiteration thinning algorithm. Graph. Models Image Process, 61(4):199-221, 1999.
[73] S. Palmer. Vision Science: Photons to Phenomenology. MIT Press, 1999.
[74] S. I. Park and J. K. Hodgins. Capturing and animating skin deformation in human motion. ACM Trans. on Graphics (Proc. SIGGRAPH), 25(3):881-889, 2006.
[75] V. Pascucci, G. Scorzelli, P.-T. Bremer, and A. Mascarenhas. Robust on-line computation of Reeb graphs: simplicity and speed. ACM Trans. on Graphics (Proc. SIGGRAPH), 26(3):Article 58, 2007.
[76] P. Perez, M. Gangnet, and A. Blake. Poisson image editing. ACM Trans. on Graphics (Proc. SIGGRAPH), 22(3):313-318, 2003.
[77] E. Praun, W. Sweldens, and P. Schroder. Consistent mesh parameterizations. In Proc. of ACM SIGGRAPH, pages 179-184, 2001.
[78] L. Ritter, W. Li, B. Curless, M. Agrawala, and D. Salesin. Painting with texture. In Eurographics Symposium on Rendering, jun 2006.
[79] S. Schaefer, T. McPhail, and J. Warren. Image deformation using moving least squares. ACM Trans. on Graphics (Proc. SIGGRAPH), 25(3):533-540, 2006.
[80] S. Schaefer and C. Yuksel. Example-based skeleton extraction. In Symp. on Geometry Processing, pages 153-162, 2007.
[81] R. Schmidt, C. Grimm, and B. Wyvill. Interactive decal compositing with discrete exponential maps. In Proc. of ACM SIGGRAPH, pages 605-613, 2006.
[82] J. Schreiner, A. Asirvatham, E. Praun, and H. Hoppe. Inter-surface mapping. ACM Trans. on Graphics (Proc. SIGGRAPH), 23(3):870-877, 2004.
[83] T. W. Sederberg, P. Gao, P. Gao, G. Wang, and H. Mu. 2-D shape blending: an intrinsic solution to the vertex path problem. In Proc. of ACM SIGGRAPH, pages 15-18, 1993.
[84] T. Serre, A. Oliva, and T. Poggio. A feedforward architecture accounts for rapid categorization. PNAS, 104(15):6424-6429, April 2007.
[85] T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, and T. Poggio. Robust object recognition with cortex-like mechanisms. IEEE Trans. Pattern Anal. Mach. Intell., 29(3):411-426, March 2007.
[86] A. Sharf, T. Lewiner, A. Shamir, and L. Kobbelt. On-the-fly curve-skeleton computation for 3D shapes. Comp. Graphics Forum, 26(3):323-328, 2007.
[87] A. Sheffer and V. Kraevoy. Pyramid coordinates for morphing and deformation. In Proc. of the 3D Data Processing, Visualization, and Transmission, pages 68-75, 2004.
[88] I. K. Shlizerman, R. Basri, and B. Nadler. 3D shape reconstruction of Mooney faces. In IEEE CVPR, pages 1-8, 2008.
[89] K. Shoemake and T. Duff. Matrix animation and polar decomposition. In Proc. of the Graphics Interface, pages 258-264, 1992.
[90] C. Stau er and W. E. L. Grimson. Learning patterns of activity using real-time tracking. IEEE Trans. Pattern Anal. Mach. Intell., 22(8):747-757, 2000.
[91] R. W. Sumner and J. Popovic. Deformation transfer for triangle meshes. In Proc. of ACM SIGGRAPH, pages 399-405, 2004.
[92] R. W. Sumner, M. Zwicker, C. Gotsman, and J. Popovic. Mesh-based inverse kinematics. ACM Trans. on Graphics (Proc. SIGGRAPH), 24(3):488-495, 2005.
[93] J. Sun, L. Yuan, J. Jia, and H.-Y. Shum. Image completion with structure propagation. ACM Trans. on Graphics (Proc. SIGGRAPH), 24(3):861-868, 2005.
[94] S. TOLEDO. Taucs: A library of sparse linear solvers, version 2.2., 2003.
[95] A. Treisman. Features and objects: the fourteenth bartlett memorial lecture. Quarterly Journal of Experimental Psychology, 40A:201-236, 1988.
[96] A. Treisman and G. Gelade. A feature-integration theory of attention. Cognitive Psychology, 12(1):97-136, 1980.
[97] J. Tsotsos. On the relative complexity of active vs. passive visual search. Int. Journal of Computer Vision, 7(2):127-141, 1992.
[98] S. Ullman. High Level Vision: Object Recognition and Visual Cognition. MIT Press, 2000.
[99] L. von Ahn, M. Blum, and J. Langford. Telling humans and computers apart automatically. Commun. ACM, 47(2):56-60, 2004.
[100] L. Wade. Automated generation of control skeletons for use in animation. PhD thesis, 2000. Adviser-Richard E. Parent.
[101] R. Y. Wang, K. Pulli, and J. Popovic. Real-time enveloping with rotational regression. ACM Trans. on Graphics (Proc. SIGGRAPH), 26(3):Article 73, 2007.
[102] Y.-S. Wang and T.-Y. Lee. Curve skeleton extraction using iterative least squares optimization. IEEE Trans. on Vis. and Comp. Graphics, 2008.
[103] B. Watson, A. Friedman, and A. McGaffey. Measuring and predicting visual delity. In Proc. of ACM SIGGRAPH, pages 213-220. ACM, 2001.
[104] O. Weber, O. Sorkine, Y. Lipman, and C. Gotsman. Context-aware skeletal shape deformation. Comp. Graphics Forum, 26(3):265-274.
[105] J. M. Wolfe. Guided search 2.0: A revised model of visual search. Psychonomic Bulletin and Review, 1(2):202-238, 1994.
[106] D. Xu, H. Zhang, H. Zhang, Q. Wang, and H. Bao. Poisson shape interpolation. In Symp. on Solid and Physical Modeling, pages 267-274, 2005.
[107] J. Xu and C. S. Kaplan. Image-guided maze construction. ACM Trans. on Graphics (Proc. SIGGRAPH), 26(3):29, 2007.
[108] H.-B. Yan, S.-M. Hu, and R. Martin. Skeleton-based shape deformation using simplex transformations. In Comp. Graphics International, pages 66-77, 2006.
[109] J. Yan and A. S. E. Ahmad. A low-cost attack on a microsoft captcha. In ACM Conf. on CCS, pages 543-554, 2008.
[110] C. Yang and H.-L. Yang. Realization of seurat's pointillism via non-photorealistic rendering. The Vis. Comp., 24(5):303-322, 2008.
[111] C.-R. Yen, M.-T. Chi, T.-Y. Lee, and W.-C. Lin. Stylized rendering using samples of a painted image. IEEE Trans. on Vis. and Comp. Graphics, 14:468-480, 2008.
[112] J. Yoon, I. Lee, and H. Kang. A Hidden-picture Puzzles Generator. In Comp. Graphics Forum, volume 27, pages 1869-1877, 2008.
[113] R. D. Zakia. Perception and Imaging. Focal Press, 2001.
[114] Y. Zhou and A. W. Toga. Efficient skeletonization of volumetric objects. IEEE Trans. on Vis. and Comp. Graphics, 5(3):196-209, 1999.