A Locally Linear Regression Model for Boundary Preserving Regularization
in Stereo Matching

Shengqi Zhu1 Li Zhang1 Hailin Jin2

1University of Wisconsin, Madison

2Adobe Systems Incorporated



We propose a novel regularization model for stereo matching that uses large neighborhood windows. The model is based on the observation that in a local neighborhood there exists a linear relationship between pixel values and disparities. Compared to the traditional boundary preserving regularization models that use adjacent pixels, the proposed model is robust to image noise and captures higher level interactions. We develop a globally optimized stereo matching algorithm based on this regularization model. The algorithm alternates between finding a quadratic upper bound of the relaxed energy function and solving the upper bound using iterative reweighted least squares. To reduce the chance of being trapped in local minima, we propose a progressive convex-hull filter to tighten the data cost relaxation. Our evaluation on the Middlebury datasets shows the effectiveness of our method in preserving boundary sharpness while keeping regions smooth. We also evaluate our method on a wide range of challenging real-world videos. Experimental results show that our method outperforms existing methods in temporal consistency.

Shengqi Zhu, Li Zhang, and Hailin Jin. A Locally Linear Regression Model for Boundary Preserving Regularization in Stereo Matching, European Conference on Computer Vision (ECCV), October, 2012. [Author's version: PDF 2.6 MB]
The original publication is available at www.springerlink.com, here.
This work is supported in part by NSF EFRI-BSBA-0937847, NSF IIS-0845916, NSF IIS-0916441, a Sloan Research Fellowship, a Packard Fellowship for Science and Engineering, and a gift donation from Adobe Systems Incorporated.
Supplementary Material
  1. Supplementary PDF: Algorithm Details and Additional Results. Download [PDF 2.6 MB]
  2. Supplementary Video: Additional Movie Results. Download [MP4 29 MB] [OGG 25 MB]
A streaming version of the Supplementary Video: