Direct Estimation of the Backward Flow

Javier Sánchez, Agustin Salgado, Nelson Monzón


The aim of this work is to propose a new method for estimating the backward flow directly from the optical flow. We assume that the optical flow has already been computed and we need to estimate the inverse mapping. This mapping is not bijective due to the presence of occlusions and disocclusions, therefore it is not possible to estimate the inverse function in the whole domain. Values in these regions has to be guessed from the available information. We propose an accurate algorithm to calculate the backward flow uniquely from the optical flow, using a simple relation. Occlusions are filled by selecting the maximum motion and disocclusions are filled with two different strategies: a min-fill strategy, which fills each disoccluded region with the minimum value around the region; and a restricted min-fill approach that selects the minimum value in a close neighborhood. In the experimental results, we show the accuracy of the method and compare the results using these two strategies.


  1. Í lvarez, L., Castan˜o, C. A., Krissian, K., Mazorra, L., Salgado, A. J., and Sánchez, J. (2007a). Symmetric Optical Flow. In Moreno Díaz, R., Pichler, F., and Quesada Arencibia, A., editors, Computer Aided Systems Theory - EUROCAST 2007, volume 4739 of Lecture Notes in Computer Science, pages 676-683. Springer Verlag, Heidelberg.
  2. Í lvarez, L., Deriche, R., Papadopoulo, T., and Sánchez, J. (2007b). Symmetrical dense optical flow estimation with occlusions detection. International Journal of Computer Vision, 75(3):371-385.
  3. Ashburner, J. (2007). A fast diffeomorphic image registration algorithm. NeuroImage, 38(1):95-113.
  4. Baker, S., Scharstein, D., Lewis, J. P., Roth, S., Black, M. J., and Szeliski, R. (2007). A database and evaluation methodology for optical flow. In International Conference on Computer Vision, pages 1-8.
  5. Cachier, P. and Rey, D. (2000). Symmetrization of the nonrigid registration problem using inversion-invariant energies: Application to multiple sclerosis. In Delp, S., DiGoia, A., and Jaramaz, B., editors, Medical Image Computing and Computer-Assisted Intervention MICCAI 2000, volume 1935 of Lecture Notes in Computer Science, pages 472-481. Springer Berlin Heidelberg.
  6. Christensen, G. and Johnson, H. (2001). Consistent image registration. IEEE Transactions on Medical Imaging, 20(7):568 -582.
  7. Lieb, D., Lookingbill, A., and Thrun, S. (2005). Adaptive road following using self-supervised learning and reverse optical flow. In Proceedings of Robotics: Science and Systems, Cambridge, USA.
  8. Lookingbill, A., Rogers, J., Lieb, D., Curry, J., and Thrun, S. (2007). Reverse optical flow for self-supervised adaptive autonomous robot navigation. International Journal of Computer Vision, 74:287-302.
  9. Salgado, A. and Sánchez, J. (2006). A temporal regularizer for large optical flow estimation. In IEEE International Conference on Image Processing ICIP, pages 1233-1236.
  10. Sánchez, J., Salgado, A., and Monzón, N. (2013). Optical flow estimation with consistent spatio-temporal coherence models. In 8th International Conference on Computer Vision Theory and Applications (VISAPP).
  11. Suzuki, K., Horiba, I., and Sugie, N. (2003). Linear-time connected-component labeling based on sequential local operations. Computer Vision and Image Understanding, 89(1):1-23.
  12. Yang, D., Li, H., Low, D. A., Deasy, J. O., and Naqa, I. E. (2008). A fast inverse consistent deformable image registration method based on symmetric optical flow computation. Physics in Medicine and Biology, 53(21):6143.

Paper Citation

in Harvard Style

Sánchez J., Salgado A. and Monzón N. (2013). Direct Estimation of the Backward Flow . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-48-8, pages 268-273. DOI: 10.5220/0004284902680273

in Bibtex Style

author={Javier Sánchez and Agustin Salgado and Nelson Monzón},
title={Direct Estimation of the Backward Flow},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)},

in EndNote Style

JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)
TI - Direct Estimation of the Backward Flow
SN - 978-989-8565-48-8
AU - Sánchez J.
AU - Salgado A.
AU - Monzón N.
PY - 2013
SP - 268
EP - 273
DO - 10.5220/0004284902680273