由於電腦硬體逐日的進步，三維場景在現今的應用越來越廣泛，舉凡遊戲、虛擬或者擴增實境、醫學相關領域等等，然而，三維場景的製作過程往往包含許多複雜的操作，使用者需要透過長時間的練習，才能建立出理想的場景，因此，如何盡量簡化，乃至於減少製作的互動流程成為了熱門討論的問題，其中又可以分為單張或多張影像的三維重建。多張影像三維重建的部分已經趨於成熟。另一方面，單張影像三維重建至今仍然是一個值得研究的問題。
單張影像三維重建由於缺乏許多重建時的必要資訊，至今為止的研究多多少少仍會有一些限制，本研究將透過互動性的方式，進行單張影像的三維重建。其中又以圖片中包含多個彼此互相遮蔽的物體為我們的著重目標。為了補齊遮蔽部分的輪廓資訊，我們假設圖片中各個物體本身具有某種對稱(Symmetry)關係，透過這個假設，我們可以利用該物體未被遮蔽的部分，重建出完整的三維模型。
在現實生活中，許多物體為了受力均衡、加工製造方便以及美觀等考量，而將物體設計成對稱(Symmetry)的結構。因此，本研究並不會因為做了對稱的假設，而侷限了此方法可以重建的三維模型種類，相反，加入對稱的訊息，將可以使本研究產生的模型更貼近現實物體的外觀。
本研究會將單張影像三維重建之問題分解為三個子問題，對稱資訊的提取、遮蔽部分的補齊以及模型表面重建。解決這些問題之後，使用者即可建立出一個三維的場景。

With the computer hardware improved days by days, 3D scenes are used more widely in many applications such as games, VR (virtual reality), AR (Augmented reality) or some other medical applications. However, reconstructing 3D scenes can be complex and tedious for a novice. It requires tons of practices to create an ideal 3D scene. For this reason, to simplify the complexity when creating 3D scenes becomes a hot topic. While there exist many well-developed methods for reconstructing 3D scenes from multiple input images. How to reconstruct 3D scenes from single input image remains a challenging problem.
Since the lack of essential information such as depth. There will be some limitations when reconstructing 3D scenes from single image. In this research, we aim to semi-automatically reconstruct 3D scenes from single image. Particularly for images that contains multiple inter-occluding objects. To complete the occluded regions of each object. We assume that each object in the input image has symmetry property. With this assumption, we can complete the occluded regions using the non-occluded part of each object and construct a contact 3D scene or model base on the completed contour.
In our daily life, many objects are designed to be symmetry for weight-balance、easy to manufacture and aesthetic reasons. Thus, the assumption of symmetry will not be a limitation in the kinds of objects that can be modeled by the proposed method. Instead, with symmetry assumption, the shape of output models will be much similar to actual object.
In this research, we will divide the reconstruction problem into three sub-problem. (i)Symmetry information extraction. (ii)Shape completion. (iii)Surface reconstruction. After we conquer these problems. We can achieve a plausible 3D scene or model.

[1] F. Yan, M. Gong, D. CohenOr, O. Deussen, and B. Chen, “Flower reconstruction from a single photo,” Comput. Graph. Forum, vol. 33, pp. 439–447, May 2014.
[2] C. Yeh, S. Huang, P. K. Jayaraman, C. Fu, and T. Lee, “Interactive highrelief reconstruction for organic and doublesided objects from a photo,” IEEE Transactions on
Visualization and Computer Graphics, vol. 23, pp. 1796–1808, July 2017.
[3] T. Chen, Z. Zhu, A. Shamir, S.M. Hu, and D. CohenOr,
“3sweep: Extracting editable objects from a single photo,” ACM Transactions on Graphics (TOG), vol. 32, 11 2013.
[4] F. Yan, M. Gong, D. CohenOr, O. Deussen, and B. Chen, “Flower reconstruction from a single photo,” Comput. Graph. Forum, vol. 33, pp. 439–447, 2014.
[5] R. Guo, C. Zou, and D. Hoiem, “Predicting complete 3d models of indoor scenes,”CoRR, vol. abs/1504.02437, 2015.
[6] D. Hoiem, A. A. Efros, and M. Hebert, “Automatic photo popup,”ACM Trans. Graph., vol. 24, pp. 577–584, July 2005.
[7] 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, May 2009.
[8] O. Barinova, V. Konushin, A. Yakubenko, K. Lee, H. Lim, and A. Konushin, “Fast automatic singleview 3d reconstruction of urban scenes,” in European Conference on
Computer Vision, pp. 100–113, Springer, 2008.
[9] T. Igarashi, S. Matsuoka, and H. Tanaka, “Teddy: a sketching interface for 3d freeform design,” in Acm siggraph 2007 courses, p. 21, ACM, 2007.
[10] B. M. Oh, M. Chen, J. Dorsey, and F. Durand, “Imagebased modeling and photo editing,”in Proceedings of the 28th annual conference on Computer graphics and interactive techniques, pp. 433–442, ACM, 2001.
[11] C. Li, H. Pan, Y. Liu, X. Tong, A. Sheffer, and W. Wang, “Bendsketch: Modeling freeform surfaces through 2d sketching,” ACM Trans. Graph., vol. 36, pp. 125:1–
125:14, July 2017.
[12] K. Yin, H. Huang, H. Zhang, M. Gong, D. CohenOr,
and B. Chen, “Morfit: Interactive surface reconstruction from incomplete point clouds with curvedriven topology and
geometry control,” ACM Trans. Graph., vol. 33, pp. 202:1–202:12, Nov. 2014.
[13] C. Yeh, P. K. Jayaraman, X. Liu, C. Fu, and T. Lee, “2.5d cartoon hair modeling and manipulation,” IEEE Transactions on Visualization and Computer Graphics, vol. 21, pp. 304–314, March 2015.
[14] N. C. T. J. Yixin Zhuang, Ming Zou, “A general and efficient method for finding cycles in 3d curve networks,” Acm Transactions on Graphics, Siggraph Asia 2013, vol. 32,
no. 6, pp. 1–10, 2013.
[15] L. Quan, P. Tan, G. Zeng, L. Yuan, J. Wang, and S. B. Kang, “Imagebased plant modeling,”in ACM Transactions on Graphics (TOG), vol. 25, pp. 599–604, ACM, 2006.
[16] P. Tan, G. Zeng, J. Wang, S. B. Kang, and L. Quan, “Imagebased tree modeling,” in ACM Transactions on Graphics (TOG), vol. 26, p. 87, ACM, 2007.
[17] D. Hoiem, A. A. Efros, and M. Hebert, “Geometric context from a single image,” in Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1, vol. 1,
pp. 654–661 Vol. 1, Oct 2005.
[18] D. Hoiem, A. A. Efros, and M. Hebert, “Recovering surface layout from an image,” Int. J. Comput. Vision, vol. 75, pp. 151–172, Oct. 2007.
[19] Q. Zeng, W. Chen, H. Wang, C. Tu, D. CohenOr, D. Lischinski, and B. Chen, “Hallucinating stereoscopy from a single image,” Comput. Graph. Forum, vol. 34, pp. 1–12, May 2015.
[20] P. L. Lions, E. Rouy, and A. Tourin,“Shapefromshading,
viscosity solutions and edges,” Numerische Mathematik, vol. 64, pp. 323–353, 12 1993.
[21] E. Prados and O. Faugeras, “Unifying approaches and removing unrealistic assumptions in shape from shading: Mathematics can help,” in Computer Vision ECCV 2004
(T. Pajdla and J. Matas, eds.), (Berlin, Heidelberg), pp. 141–154, Springer Berlin Heidelberg, 2004.
[22] Prados and Faugeras, “”perspective shape from shading” and viscosity solutions,” in Proceedings Ninth IEEE International Conference on Computer Vision, pp. 826–831 vol.2, Oct 2003.
[23] T. Igarashi, S. Matsuoka, and H. Tanaka, “Teddy: A sketching interface for 3d freeform design,” in Proceedings of the 26th Annual Conference on Computer Graphics and
Interactive Techniques, SIGGRAPH ’99, (New York, NY, USA), pp. 409–416, ACM Press/AddisonWesley Publishing Co., 1999.
[24] O. A. Karpenko and J. F. Hughes, “Smoothsketch: 3d freeform shapes from complex sketches,” ACM Trans. Graph., vol. 25, pp. 589–598, 07 2006.
[25] A. Nealen, T. Igarashi, O. Sorkine, and M. Alexa, “Fibermesh: Designing freeform surfaces with 3d curves,” ACM Trans. Graph., vol. 26, p. 41, 07 2007.
[26] C. W. A. M. van Overveld, “Painting gradients: Freeform surface design using shading patterns.,” pp. 151–158, 01 1996.
[27] B. M. Oh, M. Chen, J. Dorsey, and F. Durand, “Imagebased modeling and photo editing,” in Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH ’01, (New York, NY, USA), pp. 433–442, ACM, 2001.
[28] L. Zhang, G. DugasPhocion, J.S. Samson, and S. M. Seitz, “Singleview modelling of freeform scenes,” Journal of Visualization and Computer Animation, vol. 13, pp. 225– 235, 2002.
[29] 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.
[30] Y. Gingold, T. Igarashi, and D. Zorin, “Structured annotations for 2dto3d modeling,” ACM Trans. Graph., vol. 28, pp. 148:1–148:9, Dec. 2009.
[31] N. Kholgade, T. Simon, A. Efros, and Y. Sheikh, “3d object manipulation in a single photograph using stock 3d models,” ACM Transactions on Computer Graphics, vol. 33,
no. 4, 2014.
[32] D. Sýkora, L. Kavan, M. Čadík, O. Jamriška, A. Jacobson, B. Whited, M. Simmons, and O. SorkineHornung,“InkandRay: Basrelief meshes for adding global illumination effects to handdrawn characters,” ACM Transaction on Graphics, vol. 33, no. 2, p. 16, 2014.
[33] Y. Boykov and V. Kolmogorov, “An experimental comparison of mincut/ maxflow algorithms for energy minimization in vision,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, pp. 1124–1137, Sep. 2004.
[34] X. Liu, X. Mao, X. Yang, L. Zhang, and T.T. Wong, “Stereoscopizing cel animations,”ACM Trans. Graph., vol. 32, pp. 223:1–223:10, Nov. 2013.
[35] M. Zou, T. Ju, and N. Carr, “An algorithm for triangulating multiple 3d polygons,” in Proceedings of the Eleventh Eurographics/ACMSIGGRAPH Symposium on Geometry
Processing, SGP ’13, (AirelaVille, Switzerland, Switzerland), pp. 157–166, Eurographics Association, 2013.
[36] J. Andrews, P. Joshi, and N. A. Carr, “A linear variational system for modelling from curves,” Comput. Graph. Forum, vol. 30, pp. 1850–1861, 2011.
[37] 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, Aug. 2009.