Estimating Optimal Parameters for MRF Stereo from a Single Image Pair

@article{Zhang2007EstimatingOP,
  title={Estimating Optimal Parameters for MRF Stereo from a Single Image Pair},
  author={Li Zhang and Steven M. Seitz},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2007},
  volume={29},
  pages={331-342}
}
This paper presents a novel approach for estimating the parameters for MRF-based stereo algorithms. This approach is based on a new formulation of stereo as a maximum a posterior (MAP) problem in which both a disparity map and MRF parameters are estimated from the stereo pair itself. We present an iterative algorithm for the MAP estimation that alternates between estimating the parameters while fixing the disparity map and estimating the disparity map while fixing the parameters. The estimated… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 58 CITATIONS

Interpolation error as a quality metric for stereo: Robust, or not?

  • 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2009
VIEW 4 EXCERPTS
CITES RESULTS
HIGHLY INFLUENCED

Efficient BP stereo with automatic paramemeter estimation

  • 2008 15th IEEE International Conference on Image Processing
  • 2008
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Machine Learning Approach to Recovery of Scene Geometry from Images

  • ArXiv
  • 2010
VIEW 2 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

A Framework for Learning Depth From a Flexible Subset of Dense and Sparse Light Field Views

Jinglei Shi, Xiaoran Jiang, Christine Guillemot
  • IEEE Transactions on Image Processing
  • 2019
VIEW 2 EXCERPTS
CITES BACKGROUND

Empirical Bayesian Light-Field Stereo Matching by Robust Pseudo Random Field Modeling

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2019
VIEW 1 EXCERPT

FILTER CITATIONS BY YEAR

2007
2019

CITATION STATISTICS

  • 5 Highly Influenced Citations

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES

Fast Approximate Energy Minimization via Graph Cuts

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 2001
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Bayesian Stereo Matching

  • 2004 Conference on Computer Vision and Pattern Recognition Workshop
  • 2004
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Consistent segmentation for optical flow estimation

  • Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
  • 2005
VIEW 2 EXCERPTS

Digital Tapestry

C. Rother, S. Kumar, V. Kolmogorov, A. Blake
  • Proc. Conf. Computer Vision and Pattern Recognition, pp. 589-596, 2005.
  • 2005
VIEW 1 EXCERPT

Symmetric stereo matching for occlusion handling

  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
VIEW 1 EXCERPT