ACM Home Page
Please provide us with feedback. Feedback
Efficient reconstruction of nonrigid shape and motion from real-time 3D scanner data
Full text PdfPdf (7.74 MB)
Source
ACM Transactions on Graphics (TOG) archive
Volume 28 ,  Issue 2  (April 2009) table of contents
Article No. 15  
Year of Publication: 2009
ISSN:0730-0301
Authors
Michael Wand  Saarland University and Max Planck Institut Informatik Saarbrücken, Saarbrücken, Germany
Bart Adams  Stanford University and Katholieke Universiteit Leuven
Maksim Ovsjanikov  Stanford University
Alexander Berner  University of Tübingen, WSI/GRIS
Martin Bokeloh  University of Tübingen, WSI/GRIS
Philipp Jenke  University of Tübingen, WSI/GRIS
Leonidas Guibas  Stanford University
Hans-Peter Seidel  Max Planck Institut Informatik Saarbrücken, Saarbrücken, Germany
Andreas Schilling  University of Tübingen, WSI/GRIS
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 61,   Downloads (12 Months): 368,   Citation Count: 0
Additional Information:

appendices and supplements   abstract   references   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1516522.1516526
What is a DOI?

APPENDICES and SUPPLEMENTS
1st supplemental movie file for Efficient reconstruction of nonrigid shape and motion from real-time 3D scanner data


ABSTRACT

We present a new technique for reconstructing a single shape and its nonrigid motion from 3D scanning data. Our algorithm takes a set of time-varying unstructured sample points that capture partial views of a deforming object as input and reconstructs a single shape and a deformation field that fit the data. This representation yields dense correspondences for the whole sequence, as well as a completed 3D shape in every frame. In addition, the algorithm automatically removes spatial and temporal noise artifacts and outliers from the raw input data. Unlike previous methods, the algorithm does not require any shape template but computes a fitting shape automatically from the input data. Our reconstruction framework is based upon a novel topology-aware adaptive subspace deformation technique that allows handling long sequences with complex geometry efficiently. The algorithm accesses data in multiple sequential passes, so that long sequences can be streamed from hard disk, not being limited by main memory. We apply the technique to several benchmark datasets, significantly increasing the complexity of the data that can be handled efficiently in comparison to previous work.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
Adams, B., Ovsjanikov, M., Wand, M., Seidel, H.-P., and Guibas, L. J. 2008. Meshless modeling of deformable shapes and their motion. In ACM SIGGRAPH/Eurographics Symposium on Computer Animation.
 
2
Ahmed, N., Theobalt, C., Roessl, C., Thrun, S., and Seidel, H.-P. 2008. Dense correspondence finding for parametrization-free animation reconstruction from video. In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR).
3
4
 
5
Anguelov, D., Koller, D., Srinivasan, P., Thrun, S., Pang, H.-C., and Davis, J. 2005. The correlated correspondence algorithm for unsupervised registration of nonrigid surfaces. In Proceedings of the Conference on Advances in Neural Information Processing Systems (NIPS ).
6
 
7
Anuar, N. and Guskov, I. 2004. Extracting animated meshes with adaptive motion estimation. In Proceedings of the Vision, Modeling and Visualization Conference. 63--71.
 
8
 
9
Avriel, M. 2003. Nonlinear Programming: Analysis and Methods. Dover Publishing.
 
10
 
11
 
12
Botsch, M., Pauly, M., Wicke, M., and Gross, M. 2007. Adaptive space deformations based on rigid cells. Comput. Graph. Forum 26, 3, 339--347.
 
13
 
14
15
 
16
Chang, W. and Zwicker, M. 2008. Automatic registration for articulated shapes. Comput. Graph. Forum 27, 5.
 
17
18
 
19
Fong, P. and Buron, F. 2005. High-Resolution three-dimensional sensing of fast deforming objects. In Proceedings of the IEEE/RSI International Conference on Intelligent Robots and Systems, (IROS). 1606--1611.
 
20
Fries, T.-P. and Matthies, H. G. 2003. Classification and overview of meshfree methods. Tech. rep., TU Brunswick, Germany Nr. 2003-03.
21
 
22
 
23
Huang, Q.-X., Adams, B., Wicke, M., and Guibas, L. J. 2008. Non-Rigid registration under isometric deformations. Comput. Graph. Forum 27, 5.
 
24
König, S. and Gumhold, S. 2007. Image-Based motion compensation for structured light scanning of dynamic scenes. In EG Workshop on Dynamic 3D Imaging (Dyn3D '07).
 
25
Li, H., Sumner, R. W., and Pauly, M. 2008. Global correspondence optimization for non-rigid registration of depth scans. Comput. Graph. Forum 27, 5.
 
26
 
27
MESA. 2009. http://www.mesa-imaging.ch.
 
28
 
29
 
30
Nealen, A., Müller, M., Keiser, R., Boxerman, E., and Carlson, M. 2005. Physically based deformable models in computer graphics. In Eurographics '05 STAR Reports, 71--94.
31
32
 
33
Pekelny, Y. and Gotsman, C. 2008. Articulated object reconstruction and markerless motion capture from depth video. Comput. Graph. Forum (Proceedings of the Eurographics EG'08) 27, 2, 4.
 
34
PMD. 2009. http://www.pmdtec.com.
35
36
 
37
 
38
39
40
 
41
42
43
 
44
Süssmuth, J., Winter, M., and Greiner, G. 2008. Reconstructing animated meshes from time-varying point clouds. Comput. Graph. Forum 27, 5, 1469--1476.
45
 
46
 
47
 
48
Weise, T., Leibe, B., and Gool, L. V. 2007. Fast 3D scanning with automatic motion compensation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'07).
 
49
50
 
51
Zhang, L., Curless, B., and Seitz, S. M. 2003. Spacetime stereo: Shape recovery for dynamic scenes. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 367--374.
52
53
54
55

Collaborative Colleagues:
Michael Wand: colleagues
Bart Adams: colleagues
Maksim Ovsjanikov: colleagues
Alexander Berner: colleagues
Martin Bokeloh: colleagues
Philipp Jenke: colleagues
Leonidas Guibas: colleagues
Hans-Peter Seidel: colleagues
Andreas Schilling: colleagues