我們提出一個互動式方法使得使用者能透過單張影像重建深浮雕立體模型與旋轉立體圖。其中考慮了兩個主要及新穎的環節。第一，我們目標是可重建生活中常見且非剛性的物體，第二，我們考慮了影像中雙面結構，其兩個不同的面來自於相同物體。

我們的方法與現有的三維重建方法相比有下列幾項優點:第一，我們可以處理形狀複雜且被遮蔽住的物體，例如:人與動物。尤其我們的方法可以補足影像中雙面結構的物體因視角關係而被遮蔽的區域。第二使用者可以透過工具重建深浮雕，其物體可為凹面、凸面或凹凸面。另外我們的方法不需要額外的資料庫提供立體模型做形狀的變形，且重建對象可為一般物體，不限定要對稱或幾何形狀等結構相似度高的物體。

對於被遮蔽的區域做填補的動作，我們的方法考慮了三種在自然影像中常見的遮蔽情況，使其結果的立體模型在旋轉時之間不會有縫隙出現。使用者可以修改物體的整體斜率與膨脹曲率，接著利用最佳化方法重建三維立體模型。

最後透過我們所提出的方法重建出多張三維立體圖來做驗證，其中包含了人、動物與花等常見物體。

We introduce an interactive user-driven method to reconstruct high-relief 3D geometry from a single image for supporting the creation of rotating lenticular images.
Particularly, we consider two novel but challenging reconstruction issues: i) common non-rigid objects whose shapes are organic rather than polyhedral/symmetric, and ii) double-sided structures, where front and back sides of some curvy object parts are revealed simultaneously on image.
To address these issues, we develop a three-stage computational pipeline.
First, we construct a 2.5D model from the input image by user-driven segmentation, automatic layering, and region completion, handling three common types of occlusion.
Second, users can interactively mark-up slope and curvature cues on the image to guide our constrained optimization model to inflate and lift up the image layers.
We provide real-time preview of the inflated geometry to allow interactive editing.
Third, we stitch and optimize the inflated layers to produce a high-relief 3D model.
Compared to previous work, we can generate high-relief geometry with large viewing angles, handle complex organic objects with multiple occluded regions and varying shape profiles, and reconstruct objects with double-sided structures.
Lastly, we demonstrate the applicability of our method on a wide variety of input images with human, animals, flowers, etc.

[1] N.A. Dodgson. Autostereoscopic 3D displays. IEEE Computer, 38(8):31-36, 2005.
[2] Grayson Marshall. 3D lenticular production. http://gm3d.com/3d-lenticular-photography-production/, 2015. [Online; accessed 27-May-2015].
[3] Wojciech Matusik and Hanspeter P ster. 3D TV: A scalable system for real-time acquisition, transmission, and autostereoscopic display of dynamic scenes. ACM
Trans. Graph. (SIGGRAPH), 23(3):814-824, 2004.
[4] Derek Hoiem, Alexei A. Efros, and Martial Hebert. Automatic photo pop-up. ACM Trans. Graph. (SIGGRAPH), 24(3):577-584, 2005.
[5] Qiong Zeng, Wenzheng Chen, Huan Wang, Changhe Tu, Daniel Cohen-Or, Dani Lischinski, and Baoquan Chen. Hallucinating stereoscopy from a single image. Computer Graphics Forum (Eurographics), 34(2):1-12, 2015.
[6] Wikipedia. Relief. http://en.wikipedia.org/wiki/Relief#High_relief, 2013.[Online; accessed 17-March-2015].
[7] P. Cignoni, C. Montani, and R. Scopigno. Computer-assisted generation of bas-and high-reliefs. J. Graph. Tools, 2(3):15-28, 1997.
[8] Natasha Kholgade, Tomas Simon, Alexei Efros, and Yaser Sheikh. 3D object
manipulation in a single photograph using stock 3D models. ACM Trans. Graph.(SIGGRAPH), 33(4):127:1-12, 2014.
[9] Feilong Yan, Minglun Gong, Daniel Cohen-Or, Oliver Deussen, and Baoquan Chen. Flower reconstruction from a single photo. Computer Graphics Forum, 33(2):439-447, 2014.
[10] A. Saxena, Min Sun, and A.Y. Ng. Make3D: Learning 3D scene structure from a single still image. IEEE Trans. Pattern Anal. Mach. Intell., 31(5):824-840, 2009.
[11] Tao Chen, Zhe Zhu, Ariel Shamir, Shi-Min Hu, and Daniel Cohen-Or. 3-sweep:extracting editable objects from a single photo. ACM Trans. Graph. (SIGGRAPH Asia), 32(6):195:1-10, 2013.
[12] Daniel S ykora, Ladislav Kavan, Martin Cad k, Ond rej Jamri ska, Alec Jacobson, Brian Whited, Maryann Simmons, and Olga Sorkine-Hornung. Ink-and-ray: Bas-
relief meshes for adding global illumination e ects to hand-drawn characters. ACM Trans. Graph., 33(2):16:1-15, 2014.
[13] D. Hoiem, A.A. Efros, and M. Hebert. Geometric context from a single image. In ICCV, volume 1, pages 654{661, 2005.
[14] Derek Hoiem, AlexeiA. Efros, and Martial Hebert. Recovering surface layout from
an image. Intl. J. Comput. Vision, 75(1):151{172, 2007.
[15] Takeo Igarashi, Satoshi Matsuoka, and Hidehiko Tanaka. Teddy: A sketching
interface for 3D freeform design. In SIGGRAPH 1999, pages 409-416, New York, NY, USA, 1999.
[16] Takashi Ijiri, Shigeru Owada, and Takeo Igarashi. Seamless integration of initial sketching and subsequent detail editing in ower modeling. Computer Graphics
Forum (Eurographics), 25(3):617-624, 2006.
[17] Andrew Nealen, Takeo Igarashi, Olga Sorkine, and Marc Alexa. FiberMesh: Designing freeform surfaces with 3D curves. ACM Trans. Graph. (SIGGRAPH), 26(3):41:1-8, 2007.
[18] Yotam Gingold, Takeo Igarashi, and Denis Zorin. Structured annotations for 2D-to-3D modeling. ACM Trans. Graph. (SIGGRAPH Asia), 28(5):148:1-9, 2009.
[19] M. Prasad, A. Zisserman, and A. W. Fitzgibbon. Fast and controllable 3D modelling from silhouettes. In Eurographics, Short Paper, pages 9-12, September 2005.
[20] M. Prasad and A. Fitzgibbon. Single view reconstruction of curved surfaces. In CVPR, volume 2, pages 1345-1354, 2006.
[21] Youyi Zheng, Xiang Chen, Ming-Ming Cheng, Kun Zhou, Shi-Min Hu, and Niloy J.Mitra. Interactive images: Cuboid proxies for smart image manipulation. ACM Trans. Graph. (SIGGRAPH), 31(4):99:1-11, 2012.
[22] Youichi Horry, Ken-Ichi Anjyo, and Kiyoshi Arai. Tour into the picture: Using a spidery mesh interface to make animation from a single image. In SIGGRAPH
1997, pages 225-232, 1997.
[23] Alec Rivers, Takeo Igarashi, and Fr edo Durand. 2.5D cartoon models. ACM Trans. Graph. (SIGGRAPH), 29:59:1-7, 2010.
[24] Chih-Kuo Yeh, P.K. Jayaraman, Xiaopei Liu, Chi-Wing Fu, and Tong-Yee Lee.
2.5D cartoon hair modeling and manipulation. IEEE Trans. Vis. Comput. Graph.,21(3):304-314, 2015.
[25] Lei Zhang, Hua Huang, and Hongbo Fu. EXCOL: An EXtract-and-COmplete Layering approach to cartoon animation reusing. IEEE Trans. Vis. Comput. Graph., 18(7):1156-1169, 2012.
[26] Xueting Liu, Xiangyu Mao, Xuan Yang, Linling Zhang, and Tien-Tsin Wong. Stereoscopizing cel animations. ACM Trans. Graph. (SIGGRAPH Asia),32(6):223:1-10, 2013.
[27] Y. Boykov and V. Kolmogorov. An experimental comparison of min-cut/max-ow algorithms for energy minimization in vision. IEEE Trans. Pattern Analysis and
Machine Intelligence, 26(9):1124-1137, 2004.
[28] Stanley Osher and Ronald Fedkiw. Level set methods and dynamic implicit surfaces. Springer Science & Business Media, 2003.
[29] Antonio Criminisi, P. Perez, and K. Toyama. Region lling and object removalby exemplar-based image inpainting. IEEE Trans. Image Processing, 13(9):1200-
1212, 2004.
[30] Maxime Daisy, David Tschumperl e, and Olivier L ezoray. A fast spatial patch blending algorithm for artefact reduction in pattern-based image inpainting. In
SIGGRAPH Asia 2013 Technical Briefs, pages 8:1-4, 2013.