3D Reconstruction of Indoor Scenes using a Single RGB-D Image

Panagiotis-Alexandros Bokaris, Damien Muselet, Alain Trémeau

Abstract

The three-dimensional reconstruction of a scene is essential for the interpretation of an environment. In this paper, a novel and robust method for the 3D reconstruction of an indoor scene using a single RGB-D image is proposed. First, the layout of the scene is identified and then, a new approach for isolating the objects in the scene is presented. Its fundamental idea is the segmentation of the whole image in planar surfaces and the merging of the ones that belong to the same object. Finally, a cuboid is fitted to each segmented object by a new RANSAC-based technique. The method is applied to various scenes and is able to provide a meaningful interpretation of these scenes even in cases with strong clutter and occlusion. In addition, a new ground truth dataset, on which the proposed method is further tested, was created. The results imply that the present work outperforms recent state-of-the-art approaches not only in accuracy but also in robustness and time complexity.

References

  1. Andersen, M. R., Jensen, T., Lisouski, P., Mortensen, A., Hansen, M., Gregersen, T., and Ahrendt, P. (2012). Kinect depth sensor evaluation for computer vision applications. Technical Report ECE-TR-06, Aarhus University.
  2. Bazin, J. C., Seo, Y., Demonceaux, C., Vasseur, P., Ikeuchi, K., Kweon, I., and Pollefeys, M. (2012). Globally optimal line clustering and vanishing point estimation in manhattan world. In CVPR, pages 638-645.
  3. Coughlan, J. M. and Yuille, A. L. (1999). Manhattan world: Compass direction from a single image by bayesian inference. In ICCV, pages 941-947.
  4. Cupec, R., Nyarko, E. K., and Filko, D. (2011). Fast 2.5d mesh segmentation to approximately convex surfaces. In ECMR, pages 49-54.
  5. Dou, M., Guan, L., Frahm, J.-M., and Fuchs, H. (2013). Exploring high-level plane primitives for indoor 3d reconstruction with a hand-held rgb-d camera. In ACCV 2012 Workshops, volume 7729 of Lecture Notes in Computer Science, pages 94-108. Springer Berlin Heidelberg.
  6. Dwibedi, D., Malisiewicz, T., Badrinarayanan, V., and Rabinovich, A. (2016). Deep cuboid detection: Beyond 2d bounding boxes.
  7. Fischler, M. A. and Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM, 24(6):381-395.
  8. Hedau, V., Hoiem, D., and Forsyth, D. (2009). Recovering the spatial layout of cluttered rooms. In ICCV, pages 1849-1856.
  9. Izadi, S., Kim, D., Hilliges, O., Molyneaux, D., Newcombe, R., Kohli, P., Shotton, J., Hodges, S., Freeman, D., Davison, A., and Fitzgibbon, A. (2011). Kinectfusion: real-time 3d reconstruction and interaction using a moving depth camera. In UIST, pages 559-568.
  10. Jia, Z., Gallagher, A., Saxena, A., and Chen, T. (2013). 3dbased reasoning with blocks, support, and stability. In CVPR.
  11. Jiang, H. (2014). Finding Approximate Convex Shapes in RGBD Images, pages 582-596. Springer International Publishing, Cham.
  12. Jiang, H. and Xiao, J. (2013). A linear approach to matching cuboids in rgbd images. In CVPR.
  13. Lin, D., Fidler, S., and Urtasun, R. (2013). Holistic scene understanding for 3d object detection with rgbd cameras. In ICCV, pages 1417-1424.
  14. Mirzaei, F. and Roumeliotis, S. (2011). Optimal estimation of vanishing points in a manhattan world. In ICCV, pages 2454-2461.
  15. Neumann, D., Lugauer, F., Bauer, S., Wasza, J., and Hornegger, J. (2011). Real-time rgb-d mapping and 3-d modeling on the gpu using the random ball cover data structure. In ICCV Workshops, pages 1161-1167.
  16. Neverova, N., Muselet, D., and Trémeau, A. (2013). 2 1/2 d scene reconstruction of indoor scenes from single rgb-d images. In CCIW, pages 281-295.
  17. Piegl, L. (1991). On nurbs: a survey. IEEE Computer Graphics and Applications, 11(1):55-71.
  18. Ren, Z. and Sudderth, E. B. (2016). Three-dimensional object detection and layout prediction using clouds of oriented gradients. IEEE CVPR.
  19. Richtsfeld, A., Mörwald, T., Prankl, J., Balzer, J., Zillich, M., and Vincze, M. (2012). Towards scene understanding - object segmentation using rgbd-images. In CVWW.
  20. Schwing, A. and Urtasun, R. (2012). Efficient exact inference for 3d indoor scene understanding. In ECCV, volume 7577 of Lecture Notes in Computer Science, pages 299-313. Springer Berlin Heidelberg.
  21. Silberman, N., Hoiem, D., Kohli, P., and Fergus, R. (2012). Indoor segmentation and support inference from rgbd images. In ECCV, pages 746-760. Springer.
  22. Taylor, C. and Cowley, A. (2011). Fast scene analysis using image and range data. In ICRA, pages 3562-3567.
  23. Taylor, C. and Cowley, A. (2012). Parsing indoor scenes using rgb-d imagery. In RSS.
  24. Zhang, J., Kan, C., Schwing, A. G., and Urtasun, R. (2013). Estimating the 3d layout of indoor scenes and its clutter from depth sensors. In ICCV, pages 1273-1280.
  25. Zhang, Y., Song, S., Tan, P., and Xiao, J. (2014). PanoContext: A Whole-Room 3D Context Model for Panoramic Scene Understanding, pages 668-686. Springer International Publishing, Cham.
Download


Paper Citation


in Harvard Style

Bokaris P., Muselet D. and Trémeau A. (2017). 3D Reconstruction of Indoor Scenes using a Single RGB-D Image . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-227-1, pages 394-401. DOI: 10.5220/0006107803940401


in Bibtex Style

@conference{visapp17,
author={Panagiotis-Alexandros Bokaris and Damien Muselet and Alain Trémeau},
title={3D Reconstruction of Indoor Scenes using a Single RGB-D Image},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={394-401},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006107803940401},
isbn={978-989-758-227-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)
TI - 3D Reconstruction of Indoor Scenes using a Single RGB-D Image
SN - 978-989-758-227-1
AU - Bokaris P.
AU - Muselet D.
AU - Trémeau A.
PY - 2017
SP - 394
EP - 401
DO - 10.5220/0006107803940401