臺灣博碩士論文加值系統

我們在這篇論文中，提出了一個從多張視角影像，還原物體三維模型的新方法。此方法還原出的三維模型表面，同時具有”輪廓保留”及” 高顏色一致性”的特質。此方法由兩個階段組成，第一階段使用” 保留輪廓的體積圖切割演算法”，它是由傳統的”體積圖切割方法”修改而成的演算法。雖然它是以體積圖切割方法為基礎，但由於在此演算法中，我們利用了體積圖切割方法的結果回饋調整程式的參數，我們重複著圖形切割與調整參數這兩個步驟，直到產生的結果的輪廓完全符合輸入的影像為止。接著，我們將第一階段得到的物體表面，由第二階段的”最陡坡降演算法”來提高其顏色的一致性。
我們使用了一個真實的物體與兩個合成的物體來測試我 們的方法，改進效果從結果中可以很容易看到，在物體形狀較複雜的狀況下效果尤其顯著。

In this paper, we propose a novel method to recover a 3d object surface with silhouette preserved and high photo consistency properties from multi-view images. Our method is composed of two phases. In the first phase, ”Silhouettes Preserved Volumetric Graph Cuts”, a modified volumetric graph cuts algorithm, is used. This algorithm is on the basis of traditional volumetric graph cuts. However it adjusts the parameters according to the output of volumetric graph cuts and improves the result in an iterative way. These iterative steps will not stop until the obtained 3d surface perfectly matches the observed pictures’ silhouettes. Then, the 3d surface will be refined by Gradient Descent in the second phase. In this phase, the positions of the vertices on the surface will be updated along the normal directions to make the surface’s photo consistency optimized. In the experiment, we test our method with two synthesis models and one real object, and the improvement is obvious, especially in a complicated model case.

Contents
1. National Taiwan University i
2. master thesis i
3. Introduction - 1 -
1.1 Motivation - 1 -
1.2 Related Work - 1 -
4. Background - 5 -
2.1 Visual Hull - 5 -
2.2 Marching Cubes - 6 -
2.3 Surface Smoothing - 8 -
2.3.1 Laplacian Smoothing - 8 -
2.4 Volumetric Graph Cuts - 9 -
2.4.1 Problem One: The Lost Concavity and Convex Features - 10 -
2.4.2 Problem Two: The Unpreserved Silhouettes - 11 -
5. Our Approach - 14 -
3.1 First Phase: Silhouettes Preserved Volumetric Graph Cuts - 15 -
3.2 Second Phase: Gradient Descent using Photo Consistency - 19 -
6. Experimental Results - 22 -
7. Conclusion and Future Work - 26 -
8. Reference - 27 -

[1] D. B Goldman, B. Curless, A.n Hertzmann, and S. M. Seitz, “Shape and Spatially-Varying BRDFs from Photometric Stereo”. Proceedings of the Tenth IEEE International Conference on Computer Vision, Volume 1, Pages: 341 - 348, 2005
[2] G. Vogiatzis, C. Hern´andez, and R. Cipolla, “Reconstruction in the round using photometric normals”, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 2, Pages: 1847 – 1854, 2006
[3] S. P. Mallick, T. E. Zickler, D. J. Kriegman, and P. N. Belhumeur, “Beyond lambert: reconstructing specular surfaces using color”. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 02, 2005.
[4] G. Vogiatzis, P. H. S. Torr, and R. Cipolla, “Multi-view stereo via volumetric graph-cuts”. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Volume 2 , Pages: 391 - 398 ,2005
[5] S. Tran , and L. Davis, “3D surface reconstruction using graph cuts with surface constraints”. Proceedings of the European Conference on Computer Vision, 2006
[6] N. Birkbeck, D. Cobzas, P. Sturm, and M. Jagersand, “Variational shape and reflectance estimation under changing light and viewpoints”. Proceedings of the 9th European Conference on Computer Vision, Graz, Austria, Volume 1, Pages 536-549 - may 2006 .
[7] G. Turk and M. Levoy, “Zippered polygon meshes from range images”, International Conference on Computer Graphics and Interactive Techniques Proceedings of the 21st annual conference on Computer graphics and interactive techniques, pp. 311-318 ,1994.
[8] S. Seitz and C. Dyer, “Photorealistic scene reconstruction by voxel coloring”. Proc. Computer Vision and Pattern Recognition Conf. Page: 1067-1073, 1997.
[9] J.-Y. Bouguet and P. Perona, “3D photography on your desk.”. Proceedings of the Sixth International Conference on Computer Vision, Pages: 43 ,ICCV 1998.
[10] A. Laurentini, “The visual hull concept for silhouette based image understanding”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 16 , Issue 2 ,February, Pages: 150-162, 1994
[11] R. T. Tan and K. Ikeuchi. “Separating reflection components of textured surfaces using a single image”. Proceedings of the Ninth IEEE International Conference on Computer Vision, Volume 2, Pages: 870, 2003
[12] Apple, Inc. [Online]. Available: http://www.apple.com
[13] Lorensen, William and Harvey E. Cline. “Marching Cubes: A High Resolution 3D Surface Construction Algorithm”, International Conference on Computer Graphics and Interactive Techniques, Proceedings of the 14th annual conference on Computer graphics and interactive techniques, Pages: 163 - 169 , 1987.
[14] L. Kobbelt, S. Campagna, J. Vorsatz, and H. Seidel, ”Interactive multiresolution modeling on arbitrary meshes”, In Proceedings of SIGGRAPH, pages 105–114, 1998.
[15] G. Taubin,“A signal processing approach to fair surface design”, In proceedings of SIGGRAPH, pages 351–358, 1995.
[16] Thouis R. Jones, Frédo Durand, Mathieu Desbrun, ”Non-iterative, feature-preserving mesh smoothing”. In proceedings of SIGGRAPH , Pages: 943 – 949, 2003.
[17] Zhongping Ji, Ligang Liu, Guojin Wang.”A Global Laplacian Smoothing Approach with Feature Preservation”. In Proceedings of The 9th International Conference on Computer. Aided Design and Computer Graphics, Pages: 269 - 74 ,2005.
[18] Meshlab. http://meshlab.sourceforge.net/