Abstract
Dynamic 3D object reconstruction becomes increasingly crucial to various intelligent applications. Most existing algorithms, in spite of the accurate performances, have the problems of high cost and complex computations. In this paper, we propose a novel framework for dynamic 3D object reconstruction with a single camera in an attempt to address this problem. The gist of the proposed approach is to reduce the reconstruction problem to a pose estimation problem. We reconstruct the whole object by estimating the poses of its topological segmentations. Experiments are undertaken to validate the effectiveness of the proposed method in comparison with several state-of-art methods.
This work was jointly supported by National Natural Science Foundation of China (Grant No. U1613210) and Shenzhen Fundamental Research Programs (JCYJ20170413165528221, JCYJ2016428154842603).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Kahn, S., Bockholt, U., Kuijper, A., Fellner, D.W.: Towards precise real-time 3D difference detection for industrial applications. Comput. Ind. 64, 1115–1128 (2013)
Chiew, W.M., Lin, F., Qian, K., Seah, H.S.: A heterogeneous computing system for coupling 3D endomicroscopy with volume rendering in real-time image visualization. Comput. Ind. 65, 367–381 (2014)
Lee, J.J., Lee, B.G., Yoo, H.: Depth extraction of three-dimensional objects using block matching for slice images in synthetic aperture integral imaging. Appl. Opt. 50, 5624–5629 (2011)
Saracchini, R.F.V., Stolfi, J., Leitao, H.C.G., Atkinson, G.A., Smith, M.L.: Robust 3D face capture using example-based photometric stereo. Comput. Ind. 64, 1399–1410 (2013)
Wang, M., Hong, R., Yuan, X.T., Yan, S., Chua, T.S.: Movie2Comics: towards a lively video content presentation. IEEE Trans. Multimedia 14, 858–870 (2012)
Choi, W., Fang, Y.C., Badizadegan, K., Dasari, R.R., Feld, M.S.: Extended depth of focus in tomographic phase microscopy using a propagation algorithm. Opt. Lett. 33, 171–173 (2008)
Guillemaut, J.Y., Hilton, A.: Joint multi-layer segmentation and reconstruction for free-viewpoint video applications. Int. J. Comput. Vis. (IJCV) 93, 73–100 (2010)
Chiu, W.C., Fritz, M.: Multi-class video co-segmentation with a generative multi-video model. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)
Goldluecke, B., Magnor, M.: Space-time isosurface evolution for temporally coherent 3D reconstruction. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 350–355 (2004)
Vineet, V., et al.: Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction. In: IEEE International Conference on Robotics and Automation (ICRA) (2015)
Schönberger, J.L., Zheng, E., Frahm, J.-M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 501–518. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_31
Langguth, F., Sunkavalli, K., Hadap, S., Goesele, M.: Shading-aware multi-view stereo. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 469–485. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_29
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Jin, S., Ou, Y. (2018). Feature-Based Monocular Dynamic 3D Object Reconstruction. In: Ge, S., et al. Social Robotics. ICSR 2018. Lecture Notes in Computer Science(), vol 11357. Springer, Cham. https://doi.org/10.1007/978-3-030-05204-1_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-05204-1_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-05203-4
Online ISBN: 978-3-030-05204-1
eBook Packages: Computer ScienceComputer Science (R0)