Stereo Matching: An Outlier Confidence Approach

  title={Stereo Matching: An Outlier Confidence Approach},
  author={Li Xu and Jiaya Jia},
One of the major challenges in stereo matching is to handle pa rtial occlusions. In this paper, we introduce the Outlier Confiden ce (OC) which dynamically measures how likely one pixel is occluded. Then th e occlusion information is softly incorporated into our model. A global optim ization is applied to robustly estimating the disparities for both the occluded a n non-occluded pixels. Compared to color segmentation with plane fitting which globally partitions the image, our OC model locally… CONTINUE READING
Highly Cited
This paper has 46 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 34 extracted citations


Publications referenced by this paper.
Showing 1-10 of 24 references

Boundary matt ing for view synthesis

  • S. W. Hasinoff, S. B. Kang, R. Szeliski
  • Computer Vision and Image Understanding 103(1)
  • 2006
1 Excerpt

Similar Papers

Loading similar papers…