Temporally coherent completion of dynamic shapes

Abstract

We present a novel shape completion technique for creating temporally coherent watertight surfaces from real-time captured dynamic performances. Because of occlusions and low surface albedo, scanned mesh sequences typically exhibit large holes that persist over extended periods of time. Most conventional dynamic shape reconstruction techniques rely on template models or assume slow deformations in the input data. Our framework sidesteps these requirements and directly initializes shape completion with topology derived from the visual hull. To seal the holes with patches that are consistent with the subject's motion, we first minimize surface bending energies in each frame to ensure smooth transitions across hole boundaries. Temporally coherent dynamics of surface patches are obtained by unwarping all frames within a time window using accurate interframe correspondences. Aggregated surface samples are then filtered with a temporal visibility kernel that maximizes the use of nonoccluded surfaces. A key benefit of our shape completion strategy is that it does not rely on long-range correspondences or a template model. Consequently, our method does not suffer error accumulation typically introduced by noise, large deformations, and drastic topological changes. We illustrate the effectiveness of our method on several high-resolution scans of human performances captured with a state-of-the-art multiview 3D acquisition system.

References

1. Ahmed, N., Theobalt, C., Dobrev, P., Seidel, H.-P., and Thrun, S. 2008. Robust fusion of dynamic shape and normal capture for high-quality reconstruction of time-varying geometry. In Proceedings of the IEEE Computer Vision and Pattern Recognition Conference.
2. Alexa, M. 2003. Differential coordinates for local mesh morphing and deformation. Vis. Comput. 19, 2, 105--114.
3. Allen, B., Curless, B., and Popović, Z. 2002. Articulated body deformation from range scan data. ACM Trans. Graph. 21, 3, 612--619.
4. Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., and Davis, J. 2005. Scape: Shape completion and animation of people. ACM Trans. Graph. 24, 3, 408--416.
5. Bay, H., Tuytelaars, T., and Van Gool, L. 2008. SURF: Speeded up robust features. Comput. Vis. Image Underst. 10, 3, 346--359.
6. Botsch, M. and Sorkine, O. 2008. On linear variational surface deformation methods. IEEE Trans. Vis. Comput. Graph. 14, 1, 213--230.
7. Bradley, D., Popa, T., Sheffer, A., Heidrich, W., and Boubekeur, T. 2008. Markerless garment capture. ACM Trans. Graph. 27, 3, 99.
8. Brown, B. J. and Rusinkiewicz, S. 2007. Global non-rigid alignment of 3-d scans. ACM Trans. Graph. 26, 3, 21.
9. Brox, T., Bruhn, A., Papenberg, N., and Weickert, J. 2004. High accuracy optical flow estimation based on a theory for warping. In Proceedings of the 8th European Conference on Computer Vision. 25--36.
10. Carr, J. C., Fright, W. R., and Beatson, R. K. 1997. Surface interpolation with radial basis functions for medical imaging. IEEE Trans. Med. Imag. 16, 96--107.
11. Carranza, J., Theobalt, C., Magnor, M. A., and Seidel, H.-P. 2003. Free-viewpoint video of human actors. ACM Trans. Graph. 22, 3, 569--577.
12. Chang, W. and Zwicker, M. 2009. Range scan registration using reduced deformable models. Comput. Graph. Forum 28, 2, 447--456.
13. Chuang, M., Luo, L., Brown, B. J., Rusinkiewicz, S., and Kazhdan, M. 2009. Estimating the Laplace-Beltrami operator by restricting 3D functions. In Proceedings of the Symposium on Geometry Processing.
14. Corazza, S., Mündermann, L., Chaudhari, A., Demattio, T., Cobelli, C., and Andriacchi, T. P. 2006. A markerless motion capture system to study musculoskeletal biomechanics: Visual hull and simulated annealing approach. Ann. Biomed. Engin. 34, 6, 1019--1029.
15. Curless, B. and Levoy, M. 1996. A volumetric method for building complex models from range images. In Proceedings of SIGGRAPH. Computer Graphics Proceedings, Annual Conference Series, 303--312.
16. Davis, J., Marschner, S. R., Garr, M., and Levoy, M. 2002. Filling holes in complex surfaces using volumetric diffusion. In Proceedings of the Symposium on 3D Data Processing, Visualization, and Transmission. 428--438.
17. Davis, J., Nehab, D., Ramamoorthi, R., and Rusinkiewicz, S. 2005. Spacetime stereo: A unifying framework for depth from triangulation. IEEE Trans. Pattern Anal. Mach. Intell. 27, 2, 296--302.
18. de Aguiar, E., Stoll, C., Theobalt, C., Ahmed, N., Seidel, H.-P., and Thrun, S. 2008. Performance capture from sparse multi-view video. ACM Trans. Graph. 27, 3, 98.
19. de Aguiar, E., Theobalt, C., Stoll, C., and Seidel, H.-P. 2007. Marker-less deformable mesh tracking for human shape and motion capture. In Proceedings of the Conference on Computer Vision and Pattern Recognition.
20. Gelfand, N., Rusinkiewicz, S., Ikemoto, L., and Levoy, M. 2003. Geometrically stable sampling for the icp algorithm. In Proceedings of the International Conference on 3D Digital Imaging and Modeling. 260.
21. Held, M. 1998. Fist: Fast industrial-strength triangulation. Tech. rep.
22. Ju, T. 2009. Fixing geometric errors on polygonal models: A survey. J. Comput. Sci. Technol. 24, 1, 19--29.
23. Kazhdan, M., Bolitho, M., and Hoppe, H. 2006. Poisson surface reconstruction. In Proceedings of the Symposium on Geometry Processing.
24. Kojekine, N., Savchenko, V., Senin, M., and Hagiwara, I. 2002. Real-time 3d deformations by means of compactly supported radial basis functions. In Proceedings of Eurographics Short Papers. 35--43.
25. Li, H., Adams, B., Guibas, L. J., and Pauly, M. 2009. Robust single-view geometry and motion reconstruction. ACM Trans. Graph. 28, 5.
26. Li, H., Sumner, R. W., and Pauly, M. 2008. Global correspondence optimization for non-rigid registration of depth scans. Comput. Graph. Forum 27, 5, 1421--1430.
27. Liepa, P. 2003. Filling holes in meshes. In Proceedings of the Symposium on Geometry Processing. 200--205.
28. Mitra, N. J., Flory, S., Ovsjanikov, M., Gelfand, N., Guibas, L., and Pottmann, H. 2007. Dynamic geometry registration. In Proceedings of the Symposium on Geometry Processing. 173--182.
29. Nehab, D., Rusinkiewicz, S., Davis, J., and Ramamoorthi, R. 2005. Efficiently combining positions and normals for precise 3d geometry. ACM Trans. Graph. 24, 3, 536--543.
30. Pekelny, Y. and Gotsman, C. 2008. Articulated object reconstruction and markerless motion capture from depth video. Comput. Graph. Forum 27, 2, 399--408.
31. Sand, P., McMillan, L., and Popović, J. 2003. Continuous capture of skin deformation. ACM Trans. Graph. 22, 3, 578--586.
32. Sharf, A., Alcantara, D. A., Lewiner, T., Greif, C., Sheffer, A., Amenta, N., and Cohen-Or, D. 2008. Space-Time surface reconstruction using incompressible flow. ACM Trans. Graph. 27, 5, 1--10.
33. Sibson, R. and Stone, G. 1991. Computation of thin-plate splines. SIAM J. Sci. Statist. Comput. 12, 6, 1304--1313.
34. Starck, J. and Hilton, A. 2003. Model-based multiple view reconstruction of people. In Proceedings of the International Conference on Computer Vision. 915--922.
35. Süssmuth, J., Winter, M., and Greiner, G. 2008. Reconstructing animated meshes from time-varying point clouds. In Proceedings of the Symposium on Geometry Processing. 27, 5, 1469--1476.
36. Theobalt, C., Ahmed, N., Lensch, H., Magnor, M., and Seidel, H.-P. 2007. Seeing people in different light-joint shape, motion, and reflectance capture. IEEE Trans. Vis. Comput. Graph. 13, 4, 663--674.
37. Vlasic, D., Baran, I., Matusik, W., and Popović, J. 2008. Articulated mesh animation from multi-view silhouettes. ACM Trans. Graph. 27, 3, 97.
38. Vlasic, D., Peers, P., Baran, I., Debevec, P., Popović, J., Rusinkiewicz, S., and Matusik, W. 2009. Dynamic shape capture using multi-view photometric stereo. In SIGGRAPH Asia'09 ACM SIGGRAPH Asia 2009 Papers. 1--11.
39. Wand, M., Adams, B., Ovsjanikov, M., Berner, A., Bokeloh, M., Jenke, P., Guibas, L., Seidel, H.-P., and Schilling, A. 2009. Efficient reconstruction of nonrigid shape and motion from real-time 3d scanner data. ACM Trans. Graph. 28, 2, 15.
40. Wand, M., Jenke, P., Huang, Q., Bokeloh, M., Guibas, L., and Schilling, A. 2007. Reconstruction of deforming geometry from time-varying point clouds. In Proceedings of the Symposium on Geometry Processing.
41. Weise, T., Leibe, B., and Gool, L. V. 2007. Fast 3d scanning with automatic motion compensation. In Proceedings of the Conference on Computer Vision and Pattern Recognition.
42. Zhang, L., Curless, B., Hertzmann, A., and Seitz, S. M. 2003. Shape and motion under varying illumination: Unifying structure from motion, photometric stereo, and multi-view stereo. In Proceedings of the International Conference on Computer Vision. 618.
43. Zhang, L., Snavely, N., Curless, B., and Seitz, S. M. 2004. Spacetime faces: high resolution capture for modeling and animation. ACM Trans. Graph. 23, 3, 548--558.
44. Zheng, Q., Sharf, A., Tagliasacchi, A., Chen, B., Zhang, H., Sheffer, A., and Cohen-Or, D. 2010. Consensus skeleton for non-rigid space-time registration. Comput. Graph. Forum 29, 2, 635--644.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Computer vision

      • Computer vision problems

      • Computer vision tasks

        • Scene understanding

  • Computer graphics

    • Animation

    • Shape modeling

      • Parametric curve and surface models