TEMPORAL POST-PROCESSING METHOD FOR AUTOMATICALLY GENERATED DEPTH MAPS

Sergey Matyunin, Dmitriy Vatolin, Maxim Smirnov

2011

Abstract

Methods of automatic depth maps estimation are frequently used for 3D content creation. Such depth maps often contains errors. Depth filtering is used to decrease the noticeability of the errors during visualization. In this paper, we propose a method of temporal post-processing for automatically generated depth maps. Filtering is performed using color and motion information from the source video. A comparison of the results with test ground-truth sequences using the BI-PSNR metric is presented.

References

  1. Chen, W.-Y., Chang, Y.-L., Lin, S.-F., Ding, L.-F., and Chen, L.-G. (2005). Efficient depth image based rendering with edge dependent depth filter and interpolation. IEEE International Conference on Multimedia and Expo, 0:1314-1317.
  2. Kim, D., Min, D., and Sohn, K. (2007). Stereoscopic video generation method using motion analysis. In 3DTV Conference, pages 1-4.
  3. Kim, S.-Y., Cho, J.-H., Koschan, A., and Abidi, M. A. (2010). Spatial and temporal enhancement of depth images captured by a time-of-flight depth sensor. In International Conference on Pattern Recognition (ICPR), pages 2358-2361. IEEE.
  4. Lee, S.-B. and Ho, Y.-S. (2009). Discontinuity-adaptive depth map filtering for 3d view generation. In Proceedings of the 2nd International Conference on Immersive Telecommunications, pages 1-6.
  5. Ogale, A. S. and Aloimonos, Y. (2005). Shape and the stereo correspondence problem. International Journal of Computer Vision, 65(3):147-162.
  6. Petschnigg, G., Agrawala, M., Hoppe, H., Szeliski, R., Cohen, M., and Toyama, K. (2004). Digital photography with flash and no-flash image pairs. In SIGGRAPH, pages 664-672.
  7. Saxena, A., Chung, S. H., and Ng, A. Y. (2005). Learning depth from single monocular images. In Advances in Neural Information Processing Systems 18, pages 1161-1168. MIT Press.
  8. Scharstein, D. and Szeliski, R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 47(1-3):7-42.
  9. Scharstein, D. and Szeliski, R. (2003). High-accuracy stereo depth maps using structured light. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1:195.
  10. Simonyan, K., Grishin, S., and Vatolin, D. . (2008a). Confidence measure for block-based motion vector field. In GraphiCon, pages 110-113.
  11. Simonyan, K., Grishin, S., Vatolin, D., and Popov, D. (2008b). Fast video super-resolution via classification. In International Conference on Image Processing, pages 349-352. IEEE.
  12. Tam, W. J. and Zhang, L. (2004). Non-uniform smoothing of depth maps before image-based rendering. In Proceedings of Three-Dimensional TV, Video and Display III (ITCOM'04), volume 5599, pages 173-183.
  13. Vatolin, D., Noskov, A., and Grishin, S. (2009). MSU Brightness Independent PSNR (BI-PSNR). http://compression.ru/video/quality measure/metric plugins/bi-psnr en.htm.
  14. Zhang, G., Jia, J., Wong, T.-T., and Bao, H. (2008). Recovering consistent video depth maps via bundle optimization. In IEEE Conference on Computer Vision and Pattern Recognition, pages 1 - 8.
  15. Zhang, G., Jia, J., Wong, T.-T., and Bao, H. (2009). Consistent depth maps recovery from a video sequence. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(6):974-988.
Download


Paper Citation


in Harvard Style

Matyunin S., Vatolin D. and Smirnov M. (2011). TEMPORAL POST-PROCESSING METHOD FOR AUTOMATICALLY GENERATED DEPTH MAPS . In Proceedings of the International Conference on Imaging Theory and Applications and International Conference on Information Visualization Theory and Applications - Volume 1: IMAGAPP, (VISIGRAPP 2011) ISBN 978-989-8425-46-1, pages 33-38. DOI: 10.5220/0003318800330038


in Bibtex Style

@conference{imagapp11,
author={Sergey Matyunin and Dmitriy Vatolin and Maxim Smirnov},
title={TEMPORAL POST-PROCESSING METHOD FOR AUTOMATICALLY GENERATED DEPTH MAPS},
booktitle={Proceedings of the International Conference on Imaging Theory and Applications and International Conference on Information Visualization Theory and Applications - Volume 1: IMAGAPP, (VISIGRAPP 2011)},
year={2011},
pages={33-38},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003318800330038},
isbn={978-989-8425-46-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Imaging Theory and Applications and International Conference on Information Visualization Theory and Applications - Volume 1: IMAGAPP, (VISIGRAPP 2011)
TI - TEMPORAL POST-PROCESSING METHOD FOR AUTOMATICALLY GENERATED DEPTH MAPS
SN - 978-989-8425-46-1
AU - Matyunin S.
AU - Vatolin D.
AU - Smirnov M.
PY - 2011
SP - 33
EP - 38
DO - 10.5220/0003318800330038