Advertisement

Xtru3D: Single-View 3D Object Reconstruction from Color and Depth Data

  • Silvia Rodríguez-JiménezEmail author
  • Nicolas Burrus
  • Mohamed Abderrahim
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 458)

Abstract

3D object reconstruction from single image has been a noticeable research trend in recent years. The most common method is to rely on symmetries of real-life objects, but these are hard to compute in practice. However, a large class of everyday objects, especially when manufactured, can be generated by extruding a 2D shape through an extrusion axis. This paper proposes to exploit this property to acquire 3D object models using a single \(\mathrm{RGB} + \mathrm{Depth}\) image, such as those provided by available low-cost range cameras. It estimates the hidden parts by exploiting the geometrical properties of everyday objects, and both depth and color information are combined to refine the model of the object of interest. Experimental results on a set of 12 common objects are shown to demonstrate not only the effectiveness and simplicity of our approach, but also its applicability for tasks such as robotic grasping.

Keywords

3D reconstruction Robotics Vision RGB-D Kinect 

Notes

Acknowledgements

The research leading to these results has been funded by the HANDLE European project (FP7/2007–2013) under grant agreement ICT 231640- http://www.handle-project.eu.

References

  1. 1.
    Microsoft: Kinect for Xbox 360 (2010)Google Scholar
  2. 2.
    Kuehnle, J., Xue, Z., Stotz, M., Zoellner, J., Verl, A., Dillmann, R.: Grasping in depth maps of time-of-flight cameras. In: International Workshop on Robotic and Sensors Environments (ROSE), pp. 132–137 (2008)Google Scholar
  3. 3.
    Miller, A., Allen, P.: Graspit! a versatile simulator for robotic grasping. IEEE Robot. Autom. Mag. 11, 110–122 (2004)CrossRefGoogle Scholar
  4. 4.
    Sun, M., Kumar, S.S., Bradski, G., Savarese, S.: Toward automatic 3d generic object modeling from one single image. In: 3DIMPVT, Hangzhou, China (2011)Google Scholar
  5. 5.
    Thomas, A., Ferrari, V., Leibe, B., Tuytelaars, T., Van Gool, L.: Depth-from-recognition: inferring meta-data by cognitive feedback. In: 2007 IEEE 11th International Conference on Computer Vision. ICCV 2007, pp. 1–8. IEEE (2007)Google Scholar
  6. 6.
    Thrun, S., Wegbreit, B.: Shape from symmetry. In: 2005 Tenth IEEE International Conference on Computer Vision. ICCV 2005, vol. 2, pp. 1824–1831. IEEE (2005)Google Scholar
  7. 7.
    Bohg, J., Johnson-Roberson, M., León, B., Felip, J., Gratal, X., Bergstrom, N., Kragic, D., Morales, A.: Mind the gap-robotic grasping under incomplete observation. In: 2011 IEEE International Conference on Robotics and Automation (ICRA), pp. 686–693. IEEE (2011)Google Scholar
  8. 8.
    Marton, Z., Pangercic, D., Blodow, N., Kleinehellefort, J., Beetz, M.: General 3d modelling of novel objects from a single view. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3700–3705. IEEE (2010)Google Scholar
  9. 9.
    Benko, P., Martin, R.R., Varady, T.: Algorithms for reverse engineering boundary representation models. Comput. Aided Des. 33, 839–851 (2001)CrossRefGoogle Scholar
  10. 10.
    Diankov, R.: Automated construction of robotic manipulation programs. Ph.D. thesis, Carnegie Mellon University, Robotics Institute (2010)Google Scholar
  11. 11.
    Rusu, R., Bradski, G., Thibaux, R., Hsu, J.: Fast 3d recognition and pose using the viewpoint feature histogram. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2155–2162. IEEE (2010)Google Scholar
  12. 12.
    Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in N-d images. In: Proceedings of Eighth IEEE International Conference on Computer Vision (ICCV), vol. 1, pp. 105–112 (2001)Google Scholar
  13. 13.
    Lombaert, H., Sun, Y., Grady, L., Xu, C.: A multilevel banded graph cuts method for fast image segmentation. In: IEEE International Conference on Computer Vision (ICCV), pp. 259–265 (2005)Google Scholar
  14. 14.
    Rother, C., Kolmogorov, V., Blake, A.: “GrabCut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23, 309–314 (2004)CrossRefGoogle Scholar
  15. 15.
    Vaiapury, K., Aksay, A., Izquierdo, E.: GrabCutD: improved grabcut using depth information. In: Proceedings of the 2010 ACM Workshop on Surreal Media and Virtual Cloning. SMVC ’10, New York, NY, USA, pp. 57–62. ACM (2010)Google Scholar
  16. 16.
    Chiu, W., Blanke, U., Fritz, M.: Improving the kinect by cross-modal stereo. In: 22nd British Machine Vision Conference (BMVC), Dundee, UK (2011)Google Scholar
  17. 17.
    Oh, K.J., Yea, S., Ho, Y.S.: Hole filling method using depth based in-painting for view synthesis in free viewpoint television and 3-d video. In: Picture Coding Symposium, 2009. PCS 2009, pp. 1–4 (2009)Google Scholar
  18. 18.
    Telea, A.: An image inpainting technique based on the fast marching method. J. Graph. GPU Game Tools 9, 23–34 (2004)CrossRefGoogle Scholar
  19. 19.
    Kazhdan, M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: Symposium on Geometry Processing, pp. 61–70 (2006)Google Scholar
  20. 20.
    MeshLab: Visual Computing Lab-ISTI-CNR (2011)Google Scholar
  21. 21.
    Shum, S., Lau, W., Yuen, M., Yu, K.: Solid reconstruction from orthographic views using 2-stage extrusion. Comput. Aided Des. 33, 91–102 (2001)CrossRefGoogle Scholar
  22. 22.
    Kroemer, O., Ben Amor, H., Ewerton, M., Peters, J.: Point cloud completion using symmetries and extrusions. In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS) (2012)Google Scholar
  23. 23.
    Krainin, M., Henry, P., Ren, X., Fox, D.: Manipulator and object tracking for in hand model acquisition. In: Proceedings of the Workshop on Best Practice in 3D Perception and Modeling for Mobile Manipulation at the International Conference on Robotics Automation (ICRA) (2010)Google Scholar
  24. 24.
    Krainin, M., Curless, B., Fox, D.: Autonomous generation of complete 3d object models using next best view manipulation planning. In: IEEE International Conference on Robotics and Automation (ICRA) (2011)Google Scholar
  25. 25.
    Bimbo, J., Rodríguez-Jiménez, S., Liu, H., Burrus, N., Seneviratne, I., Abderrahim, M., Althoefer, K.: Fusing visual and tactile sensing for manipulation of unknown objects. In: Proceedings of the ICRA 2013 Mobile Manipulation Workshop on Interactive Perception (2013)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Silvia Rodríguez-Jiménez
    • 1
    Email author
  • Nicolas Burrus
    • 1
  • Mohamed Abderrahim
    • 1
  1. 1.Department of Systems Engineering and AutomationCarlos III University of MadridLeganésSpain

Personalised recommendations