3D cost aggregation with multiple minimum spanning trees for stereo matching.

Cost aggregation is one of the key steps in the stereo matching problem. In order to improve aggregation accuracy, we propose a cost-aggregation method that can embed minimum spanning tree (MST)-based support region filtering into PatchMatch 3D label search rather than aggregating on fixed size patches. However, directly combining PatchMatch label search and MST filtering is not straightforward, due to the extremely high complexity. Thus, we develop multiple MST structures for cost aggregation on plenty of 3D labels, and design the tree-level random search strategy to find possible 3D labels of each pixel. Extensive experiments show that our method reaches higher accuracy than the other existing cost-aggregation and global-optimization methods such as the 1D MST, the PatchMatch and the PatchMatch Filter, and currently ranks first on the Middlebury 3.0 benchmark.

[1]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Yafan Xu,et al.  Local stereo matching with adaptive shape support window based cost aggregation. , 2014, Applied optics.

[3]  Carsten Rother,et al.  Fast Cost-Volume Filtering for Visual Correspondence and Beyond , 2013, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  In-So Kweon,et al.  Adaptive Support-Weight Approach for Correspondence Search , 2006, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[6]  Xiang Zhou,et al.  Photometric invariant stereo matching method. , 2015, Optics express.

[7]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Duo Chen,et al.  Automatic parameter estimation based on the degree of texture overlapping in accurate cost-aggregation stereo matching for three-dimensional video display. , 2015, Applied optics.

[9]  Gauthier Lafruit,et al.  Cross-Based Local Stereo Matching Using Orthogonal Integral Images , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[10]  Yan Zhao,et al.  Stereo matching based on adaptive support-weight approach in RGB vector space. , 2012, Applied optics.

[11]  Adam Finkelstein,et al.  PatchMatch: a randomized correspondence algorithm for structural image editing , 2009, SIGGRAPH 2009.

[12]  Andrew W. Fitzgibbon,et al.  PMBP: PatchMatch Belief Propagation for Correspondence Field Estimation , 2014, International Journal of Computer Vision.

[13]  Minh N. Do,et al.  Efficient Hybrid Tree-Based Stereo Matching With Applications to Postcapture Image Refocusing , 2014, IEEE Transactions on Image Processing.

[14]  Daniel P. Huttenlocher,et al.  Efficient Graph-Based Image Segmentation , 2004, International Journal of Computer Vision.

[15]  Humberto Bustince,et al.  Aggregation functions to combine RGB color channels in stereo matching. , 2013, Optics express.