DEPTH INPAINTING WITH TENSOR VOTING USING LOCAL GEOMETRY

Mandar Kulkarni, A. N. Rajagopalan, Gerhard Rigoll

2012

Abstract

Range images captured from range scanning devices or reconstructed form optical cameras often suffer from missing regions due to occlusions, reflectivity, limited scanning area, sensor imperfections etc. In this paper, we propose a fast and simple algorithm for range map inpainting using Tensor Voting (TV) framework. From a single range image, we gather and analyze geometric information so as to estimate missing depth values. To deal with large missing regions, TV-based segmentation is initially employed as a cue for a region filling. Subsequently, we use 3D tensor voting for estimating different plane equations and pass depth estimates from all possible local planes that pass through a missing region. A final pass of tensor voting is performed to choose the best depth estimate for each point in the missing region. We demonstrate the effectiveness of our approach on synthetic as well as real data.

References

  1. Abdelhafiz, A., Riedel, B., and Niemeier, W. (2005). Towards a 3d true colored space by the fusion of laser scanner point cloud and digital photos. In Proc. of the ISPRS Working Group V/4 Workshop (3D-ARCH).
  2. Bhavsar, A. V. and Rajagopalan, A. N. (2010). Inpainting large missing regions in range images. ICPR, pages 3464-3467.
  3. Brunton, A., Wuhrer, S., and Shu, C. (2007). Image-based model completion. In Proc. of the 6th Int. Conf. on 3DIM, pages 305-311.
  4. Dias, P., Sequeira, V., Vaz, F., and Goncalves, J. (2003). Registration and fusion of intensity and range data for 3d modelling of real world scenes. In Proc. 4th Int. Conf. on 3DIM, pages 418-425.
  5. Favaro, P., Soatto, S., Burger, M., and Osher, S. J. (2008). Shape from defocus via diffusion. IEEE Trans. Pattern Anal. Mach. Intell, 30(3):518-531.
  6. Frueh, C., Jain, S., and Zakhor, A. (2005). Data processing algorithms for generating textured 3d building facade meshes from laser scans and camera images. Int. J. Comp. Vis., 61(2):159-184.
  7. Frueh, C., Sammon, R., and Zakhor, A. (2004). Automated texture mapping of 3d city models with oblique aerial imagery. Proc. 2nd Int. Symp. on 3DPVT, pages 396- 403.
  8. Guy, G. and Medioni, G. (1997). Inference of surfaces, 3d curves, and junctions from sparse, noisy, 3-d data. IEEE Trans. on PAMI, 19(11):1265-1277.
  9. Jia, J. and Tang, C.-K. (2003). Image repairing: Robust image synthesis by adaptive nd tensor voting. Conference on Computer Vision and Pattern Recognition(CVPR), pages 643-650.
  10. Lee, S. H. and Medioni, G. (1997). Non-uniform skew estimation by tensor voting. Proceedings of workshop on document Image Analysis, pages 1-4.
  11. Medioni, G., Lee, M. S., and Tang, C. K. (2000). A computational framework for segmentation and grouping. Elsevier.
  12. Scharstein, D. and Pal., C. (2007). Learning conditional random fields for stereo. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2007), pages 1-8.
  13. Scharstein, D. and Szeliski., R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47(1):7-42.
  14. Sharf, A., Alexa, M., and Cohen-Or, D. (2004). Contextbased surface completion. Proc. SIGGRAPH, 23(3):878-887.
  15. Stavrou, P., Mavridis, P., Papaioannou, G., Passalis, G., and Theoharis, T. (2006). 3d object repair using 2d algorithms. Proc. International Conference on Computational Science, pages 271-278.
  16. Xu, S., Georghiades, A., Rushmeier, H., Dorsey, J., and McMillan, L. (2006). Image guided geometry inference. Third International Symposium on 3D Data Processing, Visualization, and Transmission, pages 310- 317.
Download


Paper Citation


in Harvard Style

Kulkarni M., N. Rajagopalan A. and Rigoll G. (2012). DEPTH INPAINTING WITH TENSOR VOTING USING LOCAL GEOMETRY . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 22-30. DOI: 10.5220/0003840100220030


in Bibtex Style

@conference{visapp12,
author={Mandar Kulkarni and A. N. Rajagopalan and Gerhard Rigoll},
title={DEPTH INPAINTING WITH TENSOR VOTING USING LOCAL GEOMETRY},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={22-30},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003840100220030},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - DEPTH INPAINTING WITH TENSOR VOTING USING LOCAL GEOMETRY
SN - 978-989-8565-03-7
AU - Kulkarni M.
AU - N. Rajagopalan A.
AU - Rigoll G.
PY - 2012
SP - 22
EP - 30
DO - 10.5220/0003840100220030