Abstract
The tracking of deformation is one of the current challenges in computer vision. Analysis by Synthesis (AbS) based deformation tracking provides a way to fuse color and depth data into a single optimization problem very naturally. Previous work has shown that this can be done very efficiently using sparse synthesis. Although sparse synthesis allows AbS-based tracking to perform in real-time, it requires a great amount of problem specific customization and is limited to certain scenarios. This article introduces a new way of randomized adaptive sparsification of the reference model that adjusts the sparsification during the optimization process according to the required accuracy of the current optimization step. It will be shown that the efficiency of AbS can be increased significantly using the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
One exception can be found in [7], where the derivatives of the reprojection error are calculated for a multi-view stereo setting.
- 2.
RGB-D sequence available at http://cvlab.epfl.ch/data/dsr.
- 3.
Called registration error in [26].
- 4.
Plots are available as supplementary materials.
- 5.
Since there were no definite numbers in [26] available, we roughly estimated a lower bound based on the given Figs. 5 and 6.
References
Auger, A., Brockhoff, D., Hansen, N.: Benchmarking the (1,4)-CMA-ES with mirrored sampling and sequential selection on the noisy BBOB-2010 testbed. In: The 12th Annual Conference Companion on Genetic and Evolutionary Computation, pp. 1625–1632, July 2010
Besl, P.J., McKay, N.D.: A method for registration of 3-D shapes. IEEE Trans. Pattern Anal. Mach. Intell. 14(22), 239–256 (1992)
Bregler, C., Hertzmann, A., Biermann, H.: Recovering non-rigid 3D shape from image streams. In: CVPR, vol. 2, pp. 2690–2696 (2000)
Cagniart, C., Boyer, E., Ilic, S.: Iterative mesh deformation for dense surface tracking. In: 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, pp. 1465–1472, January 2009
Del Bue, A., Agapito, L.: Non-rigid stereo factorization. Int. J. Comput. Vis. 66(22), 193–207 (2006)
Fayad, J., Agapito, L., Del Bue, A.: Piecewise quadratic reconstruction of non-rigid surfaces from monocular sequences. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 297–310. Springer, Heidelberg (2010)
Gargallo, P., Prados, E., Sturm, P.: Minimizing the reprojection error in surface reconstruction from images. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1–8. IEEE (2007)
Hansen, N.: The CMA evolution strategy: a comparing review. In: Lozano, J.A., Larrañaga, P., Inza, I., Bengoetxea, E. (eds.) Towards a New Evolutionary Computation. Studies in Fuzziness and Soft Computing, vol. 192, pp. 75–102. Springer, Heidelberg (2006)
Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evol. Comput. 9(2), 159–195 (2001)
Helten, T., Baak, A., Bharaj, G., Müller, M., Seidel, H.P., Theobalt, C.: Personalization and evaluation of a real-time depth-based full body tracker. In: 3DV, pp. 279–286 (2013)
Innmann, M., Zollhöfer, M., Nießner, M., Theobalt, C., Stamminger, M.: VolumeDeform: real-time volumetric non-rigid reconstruction, January 2016. CoRR abs/1603.08161v2 [cs.CV]
Izadi, S., Kim, D., Hilliges, O., Molyneaux, D., Newcombe, R.A., Kohli, P., Shotton, J., Hodges, S., Freeman, D., Davison, A.J., et al.: KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera. In: UIST, pp. 559–568, January 2011
Jordt, A., Koch, R.: Fast tracking of deformable objects in depth and colour video. In: BMVC, pp. 1–11, January 2011
Jordt, A., Koch, R.: Direct model-based tracking of 3D object deformations in depth and color video. Int. J. Comput. Vis. 102(11), 239–255 (2012)
Jordt, A., Koch, R.: Reconstruction of deformation from depth and color video with explicit noise models. In: Grzegorzek, M., Theobalt, C., Koch, R., Kolb, A. (eds.) Time-of-Flight and Depth Imaging. LNCS, vol. 8200, pp. 128–146. Springer, Heidelberg (2013)
Kambhamettu, C., Goldgof, D., He, M., Laskov, P.: 3D nonrigid motion analysis under small deformations. Image Vis. Comput. 21(33), 229–245 (2003)
Li, H., Adams, B., Guibas, L.J., Pauly, M.: Robust single-view geometry and motion reconstruction. ACM Trans. Graph. 28(5), 175:1–175:10 (2009)
Qian, C., Sun, X., Wei, Y., Tang, X., Sun, J.: Realtime and robust hand tracking from depth. In: CVPR, pp. 1106–1113, January 2014
Rosenhahn, B., Kersting, U.G., Powell, K., Klette, R., Klette, G., Seidel, H.P.: A system for articulated tracking incorporating a clothing model. Mach. Vis. Appl. 18(1), 25–40 (2007)
Salzmann, M., Hartley, R.I., Fua, P.: Convex optimization for deformable surface 3-D tracking. In: ICCV, pp. 1–8, January 2007
Sharp, T., Keskin, C., Robertson, D., Taylor, J., Shotton, J.: Accurate, robust, and flexible real-time hand tracking. In: Proceedings of CHI 2015, January 2015
Shotton, J., Fitzgibbon, A.W., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from single depth images. In: CVPR, pp. 1297–1304, January 2011
Steimle, J., Jordt, A., Maes, P.: Flexpad: highly flexible bending interactions for projected handheld displays. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 237–246, January 2013
Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. Int. J. Comput. Vis. 9(22), 137–154 (1992)
Torresani, L., Hertzmann, A.: Learning non-rigid 3D shape from 2D motion. In: Advances in Neural Information Processing Systems, January 2003
Xu, W., Salzmann, M., Wang, Y., Liu, Y.: Nonrigid surface registration and completion from RGBD images. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part II. LNCS, vol. 8690, pp. 64–79. Springer, Heidelberg (2014)
Zollhöfer, M., Theobalt, C., Stamminger, M., Nießner, M., Izadi, S., Rehmann, C., Zach, C., Fisher, M., Wu, C., Fitzgibbon, A., et al.: Real-time non-rigid reconstruction using an RGB-D camera. ACM Trans. Graph. 33(44), 1–12 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Reinhold, S., Jordt, A., Koch, R. (2016). Randomly Sparsified Synthesis for Model-Based Deformation Analysis. In: Rosenhahn, B., Andres, B. (eds) Pattern Recognition. GCPR 2016. Lecture Notes in Computer Science(), vol 9796. Springer, Cham. https://doi.org/10.1007/978-3-319-45886-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-45886-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45885-4
Online ISBN: 978-3-319-45886-1
eBook Packages: Computer ScienceComputer Science (R0)