Abstract
We introduce a volumetric space-time technique for the reconstruction of moving and deforming objects from point data. The output of our method is a four-dimensional space-time solid, made up of spatial slices, each of which is a three-dimensional solid bounded by a watertight manifold. The motion of the object is described as an incompressible flow of material through time. We optimize the flow so that the distance material moves from one time frame to the next is bounded, the density of material remains constant, and the object remains compact. This formulation overcomes deficiencies in the acquired data, such as persistent occlusions, errors, and missing frames. We demonstrate the performance of our flow-based technique by reconstructing coherent sequences of watertight models from incomplete scanner data.
Supplemental Material
- de Aguiar, E., Zayer, R., Theobalt, C., Magnor, M., and Seidel, H.-P. 2007. Video-driven animation of human body scans. In 3DTV, IEEE, 1--4.Google Scholar
- Allen, B., Curless, B., and Popovic, Z. 2002. Articulated body deformation from range scan data. In Siggraph, ACM, 612--619. Google Scholar
- Anguelov, D., Koller, D., Pang, H.-C., Srinivasan, P., and Thrun, S. 2004. Recovering Articulated Object Models from 3D Range Data. In Uncertainty in Artificial Intelligence, Morgan Kaufmann, 18--26. Google Scholar
- Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., and Davis, J. 2005. SCAPE: shape completion and animation of people. Transactions on Graphics 24, 3, 408--416. Google ScholarDigital Library
- Anuar, N., and Guskov, I. 2004. Extracting Animated Meshes with Adaptive Motion Estimation. In Vision, Modeling, and Visualization, IOS, 63--71.Google Scholar
- Barron, J. L., and Thacker, N. A. 2004. Tutorial: Computing 2D and 3D Optical Flow. Tech. Rep. 012, Tina Memo.Google Scholar
- Bradley, D., Popa, T., Sheffer, A., Heidrich, W., and Boubekeur, T. 2008. Markerless Garment Capture. In Siggraph, ACM. Google Scholar
- Carranza, J., Theobalt, C., Magnor, M., and Seidel, H.-P. 2003. Free-viewpoint video of human actors. In Siggraph, ACM, 569--577. Google Scholar
- Fong, P., and Buron, F. 2005. Sensing Deforming and Moving Objects with Commercial Off the Shelf Hardware. In Computer Vision and Pattern Recognition, IEEE, 101. Google Scholar
- Goldlücke, B., and Magnor, M. 2005. Spacetime-continuous geometry meshes from multi-view video sequences. In International Conference on Image Processing, IEEE, 625--628.Google Scholar
- Goldlücke, B., Ihrke, I., Linz, C., and Magnor, M. 2007. Weighted Minimal Hypersurface Reconstruction. Transactions on Pattern Analysis and Machine Intelligence 29, 7, 1194--1208. Google ScholarDigital Library
- Golub, G. H., and Greif, C. 2003. On solving block structured indefinite linear systems. Journal on Scientific Computing 24, 6, 2076--2092. SIAM.Google ScholarDigital Library
- Greif, C., and Schötzau, D. 2006. Preconditioners for Saddle Point Linear Systems with Highly Singular (1,1) Blocks. Electronic Transactions on Numerical Analysis 22, 114--121.Google Scholar
- Grosso, E., Sandini, G., and Tistarelli, M. 1989. 3D object reconstruction using stereo and motion. Systems, Man and Cybernetics 19, 6, 1465--1476.Google ScholarCross Ref
- Gupta, N. C., and Kanal, L. N. 1995. 3D Motion Estimation from Motion Field. Artificial Intelligence 78, 1--2, 45--86. Google ScholarDigital Library
- Guskov, I., Klibanov, S., and Bryant, B. 2003. Trackable surfaces. In Symposium on Computer Animation, ACM/Eurographics, 251--257. Google ScholarDigital Library
- Hansen, P. C. 1998. Rank-Deficient and Discrete Ill-Posed Problems. SIAM. Google Scholar
- Holland, P., and Welsch, R. 1977. Robust regression using iteratively reweighted least-squares. Communications in Statistics - Theory and Methods 6, 9, 813 -- 827.Google ScholarCross Ref
- Koninckx, T. P., and van Gool, L. J. 2006. Real-Time Range Acquisition by Adaptive Structured Light. Transactions on Pattern Analysis and Machine Intelligence 28, 3, 432--445. Google ScholarDigital Library
- Levin, A., Fergus, R., Durand, F., and Freeman, W. 2007. Image and depth from a conventional camera with a coded aperture. In Siggraph, ACM, 70. Google Scholar
- Magnor, M., and Goldlücke, B. 2004. Spacetime-Coherent Geometry Reconstruction from Multiple Video Streams. In 3D Data Processing, Visualization and Transmission, IEEE, 365--372. Google Scholar
- Marschner, S. R., Guenter, B. K., and Raghupathy, S. 2000. Modeling and Rendering for Realistic Facial Animation. In Rendering Techniques, Eurographics, 231--242. Google Scholar
- Mitra, N. J., Flüry, S., Ovsjanikov, M., Gelfand, N., Guibas, L. J., and Pottmann, H. 2007. Dynamic geometry registration. In Symposium on Geometry Processing, ACM/Eurographics, 173--182. Google ScholarDigital Library
- Ohtake, Y., Belyaev, A., Alexa, M., Turk, G., and Seidel, H.-P. 2003. Multi-level partition of unity implicits. In Siggraph, ACM, 463--470. Google Scholar
- Pekelny, Y., and Gotsman, C. 2008. Articulated object reconstruction and motion capture from depth video. In Eurographics, Eurographics, to appear.Google Scholar
- Rusinkiewicz, S., Hall-Holt, O. A., and Levoy, M. 2002. Real-time 3D model acquisition. In Siggraph, ACM, 438--446. Google Scholar
- Sharf, A., Lewiner, T., Shklarski, G., Toledo, S., and Cohen-Or, D. 2007. Interactive topology-aware surface reconstruction. In Siggraph, ACM, 43. Google Scholar
- Shinya, M. 2004. Unifying Measured Point Sequences of Deforming Objects. In 3D Data Processing, Visualization and Transmission, IEEE, 904--911. Google Scholar
- Toledo, S., 2003. TAUCS: A library of sparse linear solvers. version 2.2.Google Scholar
- Ullman, S. 1979. The interpretation of structure from motion. Biological Sciences B 203, 1153, 405--426.Google Scholar
- Vedula, S., Baker, S., Rander, P., Collins, R. T., and Kanade, T. 1999. Three-Dimensional Scene Flow. In International Conference on Computer Vision, IEEE, 722--729. Google ScholarDigital Library
- Wand, M., Jenke, P., Huang, Q., Bokeloh, M., Guibas, L. J., and Schilling, A. 2007. Reconstruction of deforming geometry from time-varying point clouds. In Symposium on Geometry Processing, ACM/Eurographics, 49--58. Google ScholarDigital Library
- Wang, Y., Gupta, M., 0002, S. Z., Wang, S., Gu, X., Samaras, D., and Huang, P. 2005. High Resolution Tracking of Non-Rigid 3D Motion of Densely Sampled Data Using Harmonic Maps. In International Conference on Computer Vision, IEEE, 388--395. Google Scholar
- White, R., Crane, K., and Forsyth, D. A. 2007. Capturing and animating occluded cloth. In Siggraph, ACM, 34. Google Scholar
- Zhang, L., Brian Curless, B., and Seitz, S. M. 2003. Spacetime faces: high resolution capture for modeling and animation. In Computer Vision and Pattern Recognition, IEEE, 367--374.Google Scholar
- Zhang, L., Snavely, N., Curless, B., and Seitz, S. M. 2004. Spacetime faces: high resolution capture for modeling and animation. Transactions on Graphics 23, 3, 548--558. Google ScholarDigital Library
Index Terms
- Space-time surface reconstruction using incompressible flow
Recommendations
Space-time surface reconstruction using incompressible flow
SIGGRAPH Asia '08: ACM SIGGRAPH Asia 2008 papersWe introduce a volumetric space-time technique for the reconstruction of moving and deforming objects from point data. The output of our method is a four-dimensional space-time solid, made up of spatial slices, each of which is a three-dimensional solid ...
LV surface reconstruction from sparse TMRI using Laplacian surface deformation and optimization
ISBI'09: Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to MacroWe propose a novel framework to reconstruct the left ventricle (LV)'s 3D surface from sparse tagged-MRI (tMRI). First we acquire an initial surface mesh from a dense tMRI. Then landmarks are calculated both on contours of a specific new tMRI data and on ...
Developable surface fitting to point clouds
Given a set of data points as measurements from a developable surface, the present paper investigates the recognition and reconstruction of these objects. We investigate the set of estimated tangent planes of the data points and show that classical ...
Comments