隨著科技的發明，人們眼前不再是一般的自然場景，虛擬環境也正在快速地發展，許多真實的人事物都可以在虛擬環境中呈現，而在建造一個虛擬環境時，天空場景是非常重要的一部份，其中雲更是組成天空的重要角色，因此在虛擬環境裡，如何模擬雲，或甚至是把現實中的雲重現出來，在圖學領域中一直都是熱門討論的話題。

在虛擬環境中建造雲模型的主要方法有兩種，一種是程序方法(Procedural approach)，另一種是基於物理方法(physically based approach)，其程序方法也是目前比較受歡迎的一種方法，因為在運算成本上相較於另一種低很多，然而在參數的設定上，必須經過大量的嘗試才能產生不同種類的雲。相較於程序方法，基於物理的方法可以透過物理過程省略決定參數的部分，缺點則是在運算成本上面相比要高得多。

在虛擬環境中，建造的雲也分成是否有參考圖片，其中參考圖片的類型，又分成單張圖片和多張圖片，本研究主要討論的是如何將單張圖片針對積雲的雲類型利用粒子重建成2.5維的模型，並且不使用物理模擬，讓雲模型在維持原圖雲形狀的狀況下，讓雲能自然而不生硬的飄動。

With the development of technology and virtual environments developing rapidly, people not only see ordinary natural scenes but also see real people and things are presented in virtual environments. While building a virtual environment, sky scenes are very important, and the cloud is an important part of the sky scenes. As the result, how to simulate the cloud, or even reproduce the real cloud, has always been a hot topic in the field of graphics.
There are two major methods for building cloud models in a virtual environment, one is the procedural approach, and the other is the physically based approach. Currently the procedural approach is more popular method because the cost is much lower than the other one. However, in setting of parameters, they require a lot of attempts to generate different types of clouds. Compared with the procedural approach, the physically based approach could omit the part that determines the parameters through the physical process. The disadvantage is that the computational cost is much higher.
In the virtual environment, building the cloud is divided into referencing images or not, and the type of reference images are also divided into single image and multiple images. This study mainly discusses about how to use particles to reconstruct 2.5-dimensional cumulus cloud model from single image. We want to let clouds move smoothly by keeping the shape of the cloud model without using physical simulation.

[1] D. Hoiem, A. A. Efros and M. Hebert, "Automatic Photo Pop-up," ACM Trans. Graph, vol. 24, no. 3, pp. 577--587, 2005.
[2] A. Saxena, M. Sun and A. Y. Ng, "Make3D: Learning 3D Scene Structure from a Single Still Image," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, pp. 824--840, 2009.
[3] T. Chen, Z. Zhu, A. Shamir, S.-M. Hu and D. Cohen-Or, "3-Sweep: Extracting Editable Objects from a Single Photo," ACM Transactions on Graphics, vol. 32, 2013.
[4] C.-K. Yeh, S.-Y. Huang, P. K. Jayaraman, C.-W. Fu and T.-Y. Lee, "Interactive High-Relief Reconstruction for Organic and Double-sided Objects from a Photo," IEEE Transactions on Visualization and Computer Graphics, vol. 23, pp. 1796-1808, 2017.
[5] X. Fan, Q. Peng and M. Zhong, "3D Face Reconstruction from Single 2D Image Based on Robust Facial Feature Points Extraction and Generic Wire Frame Model," 2010.
[6] S. Choi, A.-D. Nguyen, J. Kim, S. Ahn and S. Lee, "POINT CLOUD DEFORMATION FOR SINGLE IMAGE 3D RECONSTRUCTION," IEEE International Conference on Image Processing (ICIP), pp. 2379--2383, 2019.
[7] Y. Dobashi, Y. Shinzo and T. Yamamoto, "Modeling of Clouds from a Single Photograph," Computer Graphics Forum, vol. 29, no. 7, pp. 2083--2090, 2010.
[8] C. Yuan, X. Liang, S. Hao, Y. Qi and Q. Zhao, "Modelling Cumulus Cloud Shape from a Single Image," Computer Graphics Forum, vol. 33, no. 6, pp. 288--297, 2014.
[9] Borgefors and Gunilla, "Distance transformations in digital images," Comput. Vision Graph. Image Process, vol. 34, no. 3, pp. 344--371, 1986.
[10] A. Levin, D. Lischinski and Y. Weiss, "Colorization using Optimization," ACM Transactions on Graphics, vol. 23, no. 3, pp. 689--694, 2004.
[11] N. Snavely, S. M. Seitz and R. Szeliski, "Photo Tourism: Exploring Photo Collections in 3D," ACM Transactions on Graphics, vol. 25, no. 3, pp. 835--846, 2006.
[12] J. L, Schonberger and J.-M. Frahm, "Structure-from-Motion Revisited," 2016.
[13] L. Quan, P. Tan, G. Zeng, L. Yuan, J. Wang and S. B. Kang, "Image-based Plant Modeling," ACM Transactions on Graphics, vol. 25, no. 3, pp. 599--604, 2006.
[14] C. B. Choy, D. Xu, J. Gwak, K. Chen and S. Savarese, "3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction," ECCV, pp. 628--644, 2016.
[15] H. Xie, H. Yao, X. Sun, S. Zhou and S. Zhang, "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images," IEEE ICCV, pp. 2690--2698, 2019.
[16] D. Hoiem, A. A. Efros and M. Hebert, "Geometric Context from a Single Image," Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference, vol. 1, pp. 654-661, 2005.
[17] D. Hoiem, A. A. Efros and M. Hebert, "Recovering Surface Layout from an Image," International Journal of Computer Vision, vol. 75, no. 1, pp. 151-172, 2007.
[18] T. Igarashi, S. Matsuoka and H. Tanaka, "Teddy: A Sketching Interface for 3D Freeform Design," SIGGRAPH '99 Proceedings of the 26th annual conference on Computer graphics and interactive techniques, vol. 21, pp. 409-416, 1999.
[19] O. A. Karpenko and J. F. Hughes, "SmoothSketch: 3D free-form shapes from complex sketches," ACM Trans. Graph., vol. 25, pp. 589-598, 2006.
[20] C. W. A. M. van Overveld, "Painting Gradients: Free-form Surface Design Using Shading Patterns.," 1996.
[21] B. M. Oh, M. Chen, J. Dorsey and F. Durand, "Image-Based Modeling and Photo Editing," Proceedings of the 28th annual conference on Computer graphics and interactive techniques, pp. 433-442, 2001.
[22] Y. Gingold, T. Igarashi and D. Zorin, "Structured Annotations for 2D-to-3D Modeling," ACM Trans. Graph., vol. 28, pp. 148:1--148:9, 2009.
[23] Y. Zheng, X. Chen, M.-M. Cheng, K. Zhou, S.-M. Hu and N. J. Mitra, "Interactive Images: Cuboid Proxies for Smart Image Manipulation," ACM Transactions on Graphics, vol. 31, no. 4, pp. 99:1--99:11, 2012.
[24] R. Voss, "Fourier synthesis of gaussian fractals: 1/f noises, landscapes, and flakes," SIGGRAPH'83 : Tutorial on State of the Art Image Synthesis, vol. 10, 1983.
[25] G. Y. Gardner, "Visual simulation of clouds," Computer Graphics (Proceedings of SIGGRAPH 1985), vol. 19, no. 3, pp. 297--304, 1985.
[26] D. S. Ebert, "Volumetric Modeling with Implicit Functions (A Cloud is Born)," SIGGRAPH Visual Proceedings, p. 147, 1997.
[27] J. Schpok, J. Simons, D. S. Ebert and C. Hansen, "A Real-Time Cloud Modeling, Rendering, and Animation System," ACM SIGGRAPH/Eurographics Symposium on Computer Animation, pp. 160--166, 2003.
[28] A. Elhaddad, F. Elhaddad, B. Sheng, S. Zhang, H. Sun and E. Wu, "Real-Time Cloud Simulation Using Lennard-Jones Approximation," CASA '16: Proceedings of the 29th International Conference on Computer Animation and Social Agents CASA, pp. 131--137, 2016.
[29] M. H. Lean, "Simulation and visualization of 3D particle cloud electrodynamics," IEEE Transactions on Magnetics, vol. 28, no. 2, pp. 1271--1274, 1992.
[30] S. Bi, S. Bi, X. Zeng, Y. Lu and H. Zhou, " 3-Dimensional modeling and simulation of the cloud based on cellular automata and particle system," Isprs International Journal of Geo-information, vol. 5, no. 6, 2016.
[31] Y. Xing, J. Duan, Y. Zhu and H. Wang, "Three-dimensional particle cloud simulation based on illumination model," LIDAR Imaging Detection and Target Recognition 2017, vol. 10605, pp. 483--488, 2017.
[32] Y. Dobashi, K. Iwasaki, Y. Yue and T. Nishita, "Visual simulation of clouds," Visual Informatics, vol. 1, no. 1, pp. 1--8, 2017.
[33] Y. Dobashi, T. Nishita, H. Yamashita and T. Okita, "Using metaballs to modeling and animate clouds from satellite images," The Visual Computer, vol. 15, no. 9, pp. 471--482, 1998.
[34] Y. Wexler, E. Shechtman and M. Irani, "Space-time video completion," Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004.
[35] C. Barnes, E. Shechtman, A. Finkelstein and D. B. Goldman, "PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing," ACM Transactions on Graphics (Proc. SIGGRAPH), vol. 28, no. 3, 2009.
[36] P. Pérez, M. Gangnet and A. Blake, "Poisson Image Editing," ACM SIGGRAPH 2003 Papers, pp. 313--318, 2003.
[37] D. Kraft, "A software package for sequential quadratic programming," DFVLR-FB 88-28, 1988.
[38] A. K. Jain, Fundamentals of Digital Image Processing, Prentice Hall, 1988.
[39] S. Suzuki and K. be, "Topological structural analysis of digitized binary images by border following," Comput. Vision Graphics Image Process, vol. 30, pp. 32--46, 1985.
[40] K. Perlin, "An image synthesizer," SIGGRAPH Comput. Graph, vol. 19, pp. 287--296, 1985.
[41] K. Perlin, "Improving noise," ACM, pp. 681--682, 2002.
[42] P. Virtanen, R. Gommers, T. E. Oliphant, M. Haberland, T. Reddy, D. Cournapeau, E. Burovski, P. Peterson, W. Weckesser, J. Bright, S. J. v. d. Walt, M. Brett, J. Wilson, K. J. Millman, N. Mayorov, A. R. J. Nelson, E. Jones, R. Kern, E. Larson, C. Carey, İ. Polat, Y. Feng, E. W. Moore, J. VanderPlas, D. Laxalde, J. Perktold, R. Cimrman, I. Henriksen, E. Quintero, C. R. Harris, A. M. Archibald, A. H. Ribeiro, F. Pedregosa, P. v. Mulbregt and S. 1. Contributors, "SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python," Nature Methods, vol. 17, pp. 261--272, 2020.