在這篇論文中，我們將介紹一個系統流程，能夠將一個於彩色深度影片甲中的物件轉換到另一個彩色深度影片乙。我們將物件影片影格轉換為三圍點雲並統合成一個三圍點雲模型，過濾掉異常點與作簡化後成為物體的影片變形控制點雲模型。接著由使用者於隨意場景影格中畫下簡單的筆觸標示出明顯平面後，我們藉由區域成長找出影格中屬於該平面的像素，並整合所有影格找出平面方程式與邊界。我們將這些處理過的物件影片與場景影片視為一個三維場景的資料庫。使用者可以藉由資料庫編輯全新的的場景。當編輯結束後，我們的系統將會藉由物體點雲模型挑選出最適合的影格進行圖形變形來渲染一個含有陰影與遮蔽判斷，如照片般寫實的全新影片。

In this thesis, we will introduce a system which transforms an object in RGB-D video A to another scene in RGB-D video B. By processing object videos and scene videos in specified sequences, a 3D data base for videos will be built. User can edit the novel scene with the data base. When editing is finished, our system will render a photo-realistic novel video by image warping with shadows and occlusions.

中文摘要i
Abstract ii
致謝詞 iii
Contents iv
1 Introduction 1
2 Related Work 2
3 Implementation 3
3.1 System Overview . . . . . . . . . . . . . . . 3
3.2 Object Preprocess . . . . . . . . . . . . . . 4
3.2.1 Point Cloud Integration . . . . . . . 4
3.2.2 Model Down-scaling . . . . . . . . . 4
3.3 Scene Preprocess . . . . . . . . . . . . . . . 5
3.3.1 Segment-based Region Growing . . . 5
3.3.2 Supporting Plane and Boundary . . 7
3.4 Manipulation . . . . . . . . . . . . . . . . . 8
3.5 Rendering by Image Warping . . . . . . . . 9
3.5.1 Control Point and Optimal Frame . 9
3.5.2 Shadow Map Synthesis . . . . . . . . 10
3.5.3 Layer Composition . . . . . . . . . . 11
4 Results and Discussion 12
5 Conclusion 14
Bibliography 15

[1] Dragomir Anguelov, Praveen Srinivasan, Daphne
Koller, Sebastian Thrun, Jim Rodgers, and James
Davis. Scape: shape completion and animation
of people. ACM Trans. Graph., 24(3):408–
416, 2005. URL http://dblp.uni-trier.de/db/
journals/tog/tog24.html#AnguelovSKTRD05.
[2] Thomas Helten, Andreas Baak, Gaurav Bharaj,
Meinard Muller, Hans-Peter Seidel, and Christian
Theobalt. Personalization and evaluation of a realtime
depth-based full body tracker. In Proceedings
of the 2013 International Conference on 3D
Vision, 3DV ’13, pages 279–286, Washington, DC,
USA, 2013. IEEE Computer Society. ISBN 978-
0-7695-5067-1. doi: 10.1109/3DV.2013.44. URL
http://dx.doi.org/10.1109/3DV.2013.44.
[3] Chenglei Wu, Kiran Varanasi, and Christian
Theobalt. Full body performance capture under
uncontrolled and varying illumination: A shadingbased
approach. In Proceedings of the 12th European
Conference on Computer Vision - Volume
Part IV, ECCV’12, pages 757–770, Berlin, Heidelberg,
2012. Springer-Verlag. ISBN 978-3-642-33764-
2. doi: 10.1007/978-3-642-33765-9_54. URL http:
//dx.doi.org/10.1007/978-3-642-33765-9_54.
[4] A. Weiss, D. Hirshberg, and M.J. Black. Home 3d
body scans from noisy image and range data. In
Computer Vision (ICCV), 2011 IEEE International
Conference on, pages 1951–1958, Nov 2011. doi:
10.1109/ICCV.2011.6126465.
[5] Richard A. Newcombe, Shahram Izadi, Otmar
Hilliges, David Molyneaux, David Kim, Andrew J.
Davison, Pushmeet Kohli, Jamie Shotton, Steve
Hodges, and Andrew W. Fitzgibbon. Kinectfusion:
Real-time dense surface mapping and tracking. In
10th IEEE International Symposium on Mixed and
Augmented Reality, ISMAR 2011, Basel, Switzerland,
October 26-29, 2011, pages 127–136, 2011.
doi: 10.1109/ISMAR.2011.6092378. URL http://
dx.doi.org/10.1109/ISMAR.2011.6092378.
[6] Robert Held, Ankit Gupta, Brian Curless, and Maneesh
Agrawala. 3d puppetry: A kinect-based interface
for 3d animation. In Proceedings of the
25th Annual ACM Symposium on User Interface
Software and Technology, UIST ’12, pages 423–434,
New York, NY, USA, 2012. ACM. ISBN 978-1-
4503-1580-7. doi: 10.1145/2380116.2380170. URL
http://doi.acm.org/10.1145/2380116.2380170.
[7] Jiawen Chen, Dennis Bautembach, and Shahram
Izadi. Scalable real-time volumetric surface reconstruction.
ACM Trans. Graph., 32(4):113:1–113:16,
July 2013. URL http://research.microsoft.com/
apps/pubs/default.aspx?id=198579.
[8] C. Y. Ren, V. A. Prisacariu, D. W. Murray, and I. D.
Reid. STAR3D: Simultaneous tracking and reconstruction
of 3D objects using RGB-D data. In IEEE
International Conference on Computer Vision, pages
1561–1568, Dec 2013. doi: 10.1109/ICCV.2013.197.
[9] Xue Bai, Jue Wang, David Simons, and Guillermo
Sapiro. Video snapcut: Robust video object cutout
using localized classifiers. 28(3):70:1–70:11, 2009.
[10] Radu Bogdan Rusu and Steve Cousins. 3D is here:
Point Cloud Library (PCL). In IEEE International
Conference on Robotics and Automation (ICRA),
Shanghai, China, May 9-13 2011.
[11] Radhakrishna Achanta, Appu Shaji, Kevin Smith,
Aurélien Lucchi, Pascal Fua, and Sabine Süsstrunk.
SLIC Superpixels. Technical report, EPFL, 2010.
[12] Martin A. Fischler and Robert C. Bolles. Random
sample consensus: A paradigm for model fitting with
applications to image analysis and automated cartography.
Commun. ACM, 24(6):381–395, June 1981.
ISSN 0001-0782. doi: 10.1145/358669.358692. URL
http://doi.acm.org/10.1145/358669.358692.
[13] Qian-Yi Zhou and Vladlen Koltun. Color map
optimization for 3d reconstruction with consumer
depth cameras. ACM Trans. Graph., 33(4):155:1–
155:10, July 2014. ISSN 0730-0301. doi: 10.1145/
2601097.2601134. URL http://doi.acm.org/10.
1145/2601097.2601134.