像素藝術是一種現代的數位藝術，圖形需要在有限的空間下用像素和顏色去表達。在本篇論文中，我們探討了兩個關於像素藝術的應用。
在第一部份，我們提出了一個新穎的計算框架，可以自動化的從像素藝術中產生樂高模型。樂高是一種很受歡迎的玩具，它提供了一種很方便的方式去塑造幾何模型。有別於以往的研究都是注重在3D 模型的轉換上，像素藝術具有很豐富的視覺內涵可以用來結合樂高的設計，除此之外像素藝術的性質和如何去用來建立模型也是一個新的挑戰。在這個研究中，我們在同時考慮到視覺的品質和最後模型的穩定性下建立了一套設計標準。
在第二部分，我們提出了一個針對像素藝術特製的動畫框架。繪製像素藝術是一個很耗費時間和需要技巧的工作，因為需要用有限的像素去表達複雜的形狀。不意外地，繪製像素藝術動畫是更困難的，因為需要額外再考慮影格間的關聯性。目前的系統都需要使用者一個影格一個影格的繪製，這是一件非常耗時而且容易出錯的工作。我們的系統根據傳統的關鍵影格框架和最新的圖形變形技術去產生初始動畫，之後在同時考慮到的視覺品質和影格間的關聯性下，去優化每條像素線條。

Pixel art is a modern digital art in which high resolution images are abstracted into low resolution pixelated outputs using concise outlines and reduced color palettes. In this work, we conduct research on two applications of Pixel art.
In the first part, we present a novel computational framework to automatically construct brick sculptures from pixel art. LEGO®, a popular brick-based toy construction system, provides an affordable and convenient way of fabricating geometric shapes. In contrast to previous efforts that focus on 3D models, pixel art contains rich visual contents for generating engaging LEGO designs. On the other hand, the characteristics of pixel art and corresponding brick sculpture pose new challenges to the design process. In this work, we implement a set of design guidelines concerning the visual quality as well as the structural stability of built sculptures.
In the second part, we present a novel animation framework tailored to pixel art images. Creating pixel art is a labor intensive and skill-demanding process due to the challenge of using limited pixels to represent complicated shapes. Not surprisingly, generating pixel art animation is even harder given the additional constraints imposed in the temporal domain. Existing systems typically request users to craft individual pixels frame by frame, which is a tedious and error-prone process. Our system bases on conventional keyframe animation framework and state-of-the-art image warping techniques to generate an initial animation sequence. The system then jointly optimizes the prominent feature lines of individual frames respecting three metrics that capture the quality of the animation sequence in both spatial and temporal domains.

誌謝辭i
中文摘要 ii
Abstract iii
Contents iv
List of Figures vi
I Brick Sculptures Construction 1
1 Introduction 2
2 Related Works 5
3 Implementation 7
3.1 Designing Brick Sculpture from Pixel Art 7
3.2 Overview 8
3.3 Algorithm 9
3.3.1 Generating Balanced Pixel Art 9
3.3.2 Mapping Colors from Pixels to Bricks 11
3.3.3 Constructing Stable Brick Sculpture 13
3.3.3.1 Resolving Dangling Parts 13
3.3.3.2 Optimizing Brick Layout 14
4 Results and Discussion 17
5 Conclusion and Future Work 21
II Feature-Aware Animation 22
6 Introduction 23
7 Related Works 26
8 Implementation 28
8.1 System Overview 28
8.2 Feature-Aware Optimization 30
8.2.1 Quality metrics 30
8.2.2 Optimization 35
9 Results and Evaluation 39
9.1 Evaluation 39
9.2 Limitations 42
10 Conclusion and Future Work 43
III Appendix 44
A Feature Line Vectorization 45
B Balanced Pixel Art 46
Bibliography 47

[1] Rebecca Gower, Agnes Heydtmann, and Henrik Petersen. Lego: Automated model
construction. In 32nd European Study Group with Industry, pages 81–94, 1998.
[2] Stefanie Mueller, Tobias Mohr, Kerstin Guenther, Johannes Frohnhofen, and
Patrick Baudisch. fabrickation: Fast 3d printing of functional objects by integrating
construction kit building blocks. In SIGCHI, pages 3827–3834, 2014.
[3] Jae Woo Kim, Kyung Kyu Kang, and Ji Hyoung Lee. Survey on automated lego
assembly construction. In Poster Proceedings of WSCG, pages 89–96, 2014.
[4] Neil Gershenfeld. Fab: The Coming Revolution on Your Desktop–from Personal
Computers to Personal Fabrication. Basic Books, Inc., 2007.
[5] Ligang Liu, Ariel Shamir, Charlie Wang, and Emily Whitening. 3d printing oriented
design: Geometry and optimization. In SIGGRAPH Asia 2014 Courses, 2014.
[6] Ondrej Stava, Juraj Vanek, Bedrich Benes, Nathan Carr, and Radomír Měch. Stress
relief: Improving structural strength of 3d printable objects. ACM Trans. Graph.
(Proc. SIGGRAPH), 31(4):48:1–48:11, 2012.
[7] Romain Prévost, Emily Whiting, Sylvain Lefebvre, and Olga Sorkine-Hornung.
Make it stand: Balancing shapes for 3d fabrication. ACM Trans. Graph. (Proc.
SIGGRAPH), 32(4):81:1–81:10, 2013.
[8] Weiming Wang, Tuanfeng Y. Wang, Zhouwang Yang, Ligang Liu, Xin Tong, Weihua
Tong, Jiansong Deng, Falai Chen, and Xiuping Liu. Cost-effective printing of 3d
objects with skin-frame structures. ACM Trans. Graph. (Proc. SIGGRAPH Asia),
32(6):177:1–177:10, 2013.
[9] Lin Lu, Andrei Sharf, Haisen Zhao, Yuan Wei, Qingnan Fan, Xuelin Chen, Yann
Savoye, Changhe Tu, Daniel Cohen-Or, and Baoquan Chen. Build-to-last: Strength
to weight 3d printed objects. ACM Trans. Graph. (Proc. SIGGRAPH), 33(4):97:1–
97:10, 2014.
[10] Linjie Luo, Ilya Baran, Szymon Rusinkiewicz, and Wojciech Matusik. Chopper:
Partitioning models into 3d-printable parts. ACM Trans. Graph. (Proc. SIGGRAPH
Asia), 31(6):129:1–129:9, 2012.
[11] Martin Kilian, Simon Flöry, Zhonggui Chen, Niloy J. Mitra, Alla Sheffer, and
Helmut Pottmann. Curved folding. ACM Trans. Graph. (Proc. SIGGRAPH), 27
(3):75:1–75:9, 2008.
[12] Xian-Ying Li, Chao-Hui Shen, Shi-Sheng Huang, Tao Ju, and Shi-Min Hu. Popup:
Automatic paper architectures from 3d models. ACM Trans. Graph. (Proc. SIGGRAPH),
29(4):111:1–111:9, 2010.
[13] Xian-Ying Li, Tao Ju, Yan Gu, and Shi-Min Hu. A geometric study of v-style
pop-ups: Theories and algorithms. ACM Trans. Graph. (Proc. SIGGRAPH), 30
(4):98:1–98:10, 2011. ISSN 0730-0301.
[14] Shiqing Xin, Chi-Fu Lai, Chi-Wing Fu, Tien-Tsin Wong, Ying He, and Daniel
Cohen-Or. Making burr puzzles from 3D models. ACM Trans. Graph. (Proc.
SIGGRAPH), 30(4):97:1–97:8, 2011.
[15] Peng Song, Chi-Wing Fu, and Daniel Cohen-Or. Recursive interlocking puzzles.
ACM Trans. Graph. (Proc. SIGGRAPH Asia), 31(6):128:1–128:10, 2012.
[16] Niloy J. Mitra and Mark Pauly. Shadow art. ACM Trans. Graph. (Proc. SIGGRAPH
Asia), 28(5):156:1–156:7, 2009.
[17] Pavel Petrovic. Solving lego brick layout problem using evolutionary algorithms.
Norwegian University of Science and Technology, Technical Report, 2001.
[18] David Winkler. Automated brick layout. BrickFest, 2005.
http://www.brickshelf.com/gallery/happyfrosh/BrickFest2005/
automatedbricklayout.pdf.
[19] Lynette van Zijl and Eugene Smal. Cellular automata with cell clustering. In
Proceedings of Automata: Theory and Applications of Cellular Automata, pages
425–440, 2008.
[20] Romain Testuz, Yuliy Schwartzburg, and Mark Pauly. Automatic generation of
constructable brick sculptures. In Proceedings of Eurographics, short papers, pages
81–84, 2013.
[21] Jhen-Yao Hong, Der-Lor Way, Zen-Chung Shih, Wen-Kai Tai, and Chin-Chen
Chang. Inner engraving for the creation of a balanced lego sculpture. The Visual
Computer, pages 1–10, 2015.
[22] Takeo Igarashi, Tomer Moscovich, and John F. Hughes. As-rigid-as-possible shape
manipulation. ACM Trans. Graph. (Proc. SIGGRAPH), 24(3):1134–1141, 2005.
[23] Guo-Xin Zhang, Ming-Ming Cheng, Shi-Min Hu, and Ralph R. Martin. A shapepreserving
approach to image resizing. Comp. Graphics Forum, 28(7):1897–1906,
2009.
[24] PicToBrick, 2010. http://www.pictobrick.de/en/pictobrick.shtml.
[25] Yuri Boykov, Olga Veksler, and Ramin Zabih. Fast approximate energy minimization
via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell., 23(11):1222–1239,
2001.
[26] Michael Rubinstein, Diego Gutierrez, Olga Sorkine, and Ariel Shamir. A comparative
study of image retargeting. ACM Trans. Graph. (Proc. SIGGRAPH Asia), 29
(6):160:1–160:10, 2010.
[27] Sheng-Jie Luo, Yonghao Yue, Chun-Kai Huang, Yu-Huan Chung, Sei Imai, Tomoyuki
Nishita, and Bing-Yu Chen. Legolization: Optimizing lego designs. ACM
Trans. Graph. (Proc. SIGGRAPH Asia), 34(6):222:1–222:12, 2015.
[28] Kai Vermehr, Steffen Sauerteig, and Svend Smital. eboy. hello.eboy.com, 2012.
[29] Mike Parent and Edgar Muniz. Spriter. brashmonkey.com, 2012.
[30] Julian Descottes. Piskel. www.piskelapp.com.
[31] Derek Yu. Pixel art tutorial. makegames.tumblr.com/post/42648699708/pixel-arttutorial,
2013.
[32] J. E. Bresenham. Algorithm for computer control of a digital plotter. IBM Syst.
J., 4(1):25–30, 1965.
[33] Jack Bresenham. A linear algorithm for incremental digital display of circular arcs.
Commun. ACM, 20(2):100–106, 1977.
[34] Xiaolin Wu. An efficient antialiasing technique. In Proceedings of the 18th Annual
Conference on Computer Graphics and Interactive Techniques, SIGGRAPH ’91,
pages 143–152, 1991.
[35] Timothy Gerstner, Doug DeCarlo, Marc Alexa, Adam Finkelstein, Yotam Gingold,
and Andrew Nealen. Pixelated image abstraction. In Proc. of NPAR, pages 29–36.
Eurographics Association, 2012.
[36] Johannes Kopf, Ariel Shamir, and Pieter Peers. Content-adaptive image downscaling.
ACM Trans. Graph. (Proc. SIGGRAPH Asia), 32(6):173:1–173:8, 2013.
[37] Tiffany C. Inglis and Craig S. Kaplan. Pixelating vector line art. In Proc. of NPAR,
pages 21–28, 2012.
[38] Tiffany C. Inglis, Daniel Vogel, and Craig S. Kaplan. Rasterizing and antialiasing
vector line art in the pixel art style. In Proc. of NPAR, pages 25–32, 2013.
[39] Peter Selinger. Potrace: a polygon-based tracing algorithm. potrace.
sourceforge.net, 2003.
[40] ADOBE, INC. Adobe illustrator cs5. www.adobe.com/products/illustrator.html,
2010.
[41] Vector Magic, INC. Vector magic. vectormajig.com, 2010.
[42] Johannes Kopf and Dani Lischinski. Depixelizing pixel art. ACM Trans. Graph.
(Proc. SIGGRAPH), 30(4):99:1–99:8, 2011.
[43] Adrien Bousseau, Fabrice Neyret, Joëlle Thollot, and David Salesin. Video watercolorization
using bidirectional texture advection. ACM Trans. Graph. (Proc.
SIGGRAPH), 26(3), 2007.
[44] Peter O’Donovan and Aaron Hertzmann. Anipaint: Interactive painterly animation
from video. IEEE Trans. on Vis. and Comp. Graphics, 18(3):475–487, 2012.
[45] Gioacchino Noris, Daniel Sỳkora, Stelian Coros, Brian Whited, Maryann Simmons,
Alexander Hornung, M Gross, and Robert W Sumner. Temporal noise control for
sketchy animation. In Proc. of NPAR, pages 93–98, 2011.
[46] Pierre Bénard, Forrester Cole, Aleksey Golovinskiy, and Adam Finkelstein. Selfsimilar
texture for coherent line stylization. In Proc. of NPAR, 2010.
[47] Pierre Bénard, Adrien Bousseau, and Joëlle Thollot. State-of-the-art report on
temporal coherence for stylized animations. In Comp. Graphics Forum, volume 30,
pages 2367–2386, 2011.
[48] Jonathan Richard Shewchuk. Triangle: Engineering a 2d quality mesh generator
and delaunay triangulator. In Selected Papers from the Workshop on Applied
Computational Geormetry, Towards Geometric Engineering, FCRC ’96/WACG ’96,
pages 203–222, 1996.
[49] Marc Alexa, Daniel Cohen-Or, and David Levin. As-rigid-as-possible shape interpolation.
In Proceedings of the 27th Annual Conference on Computer Graphics and
Interactive Techniques, SIGGRAPH ’00, pages 157–164, 2000.
[50] Esther M. Arkin, L. Paul Chew, David P. Huttenlocher, Klara Kedem, and Joseph
S. B. Mitchell. An efficiently computable metric for comparing polygonal shapes.
In Proceedings of the First Annual ACM-SIAM Symposium on Discrete Algorithms,
SODA ’90, pages 129–137, 1990.
[51] Alec Rivers, Takeo Igarashi, and Frédo Durand. 2.5D cartoon models. ACM Trans.
Graph. (Proc. SIGGRAPH), 29(4):59:1–59:7, 2010.
[52] Chih-Kuo Yeh, Pradeep Kumar Jayaraman, Xiaopei Liu, Chi-Wing Fu, and Tong-
Yee Lee. 2.5D cartoon hair modeling and manipulation. IEEE Trans. on Vis. and
Comp. Graphics, 21(3):304–314, 2015.