Cross-scale cost aggregation integrating intrascale smoothness constraint with weighted least squares in stereo matching

Stereo matching based on multi-scale fusion and multi-type support regions

Obtaining accurate disparity values in textureless and texture-free regions is a very challenging task. To solve this problem, we present a novel algorithm. First, we use the guided filter method to fuse the color cost volume and the gradient cost volume. Second, we use three types of image category information to merge the different scale disparity maps and obtain the primary disparity map. Third, during the disparity refinement procedure, we also utilize the three types of category information to define different support regions and assign different weights for pixels remaining to be refined. Extensive experiments show that the performance of our method is not inferior to many state-of-the-art methods on the Middlebury data set.

Disparity-selective stereo matching using correlation confidence measure

Recently, the cost-volume filtering (CVF) methods for local stereo matching have provided fast and accurate results compared to those of the other method. However, CVF still causes incorrect results in the occlusion and texture-free regions. In particular, cost aggregation by pixel units involves complex computation because of its dependence on the image resolution and search range. This paper presents a robust stereo matching method for occluded regions. First, we generate cost volumes using the CENSUS transform and the scale-invariant feature transform (SIFT). Then, label-based cost volumes are aggregated using adaptive support weight and the simple linear iterative clustering (SLIC) scheme from two generated cost volumes. In order to obtain optimal disparity by two label-based cost volumes, we select the disparity corresponding to high confidence similarity of CENSUS or SIFT with minimum cost point. Experimental results show that our method estimates the optimal disparity in occlusion information, which exists only in the scene of one of the stereo pairs.

Improving stereo matching algorithm with adaptive cross-scale cost aggregation

Human beings process stereoscopic correspondence across multiple purposes like robot navigation, automatic driving, and virtual or augmented reality. However, this bioinspiration is ignored by state-of-the-art dense stereo correspondence matching methods. Cost aggregation is one of the critical steps in the stereo matching method. In this article, we propose an optimized cross-scale cost aggregation scheme with coarse-to-fine strategy for stereo matching. This scheme implements cross-scale cost aggregation with the smoothness constraint on neighborhood cost, which essentially extends the idea of the inter-scale and intra-scale consistency constraints to increase the matching accuracy. The neighborhood costs are not only used in the intra-scale consistency to ensure that the regularized costs vary smoothly in an eight-connected neighbors region but also incorporated with inter-scale consistency to optimize the disparity estimation. Additionally, the improved method introduces an adaptive scheme in each scale with different aggregation methods. Finally, experimental results evaluated both on classic Middlebury and Middlebury 2014 data sets show that the proposed method performs better than the cross-scale cost aggregation. The whole stereo correspondence algorithm achieves competitive performance in terms of both matching accuracy and computational efficiency. An extensive comparison, including the KITTI benchmark, illustrates the better performance of the proposed method also.