Stereo matching plays an essential role in various computer vision applications. Cost volume is the crucial part in disparity estimation for measuring the similarity between the left-right feature locations. However, most previous cost volume construction based on concatenation or pixel-wise correlation lack of local similarity, leads to an unsatisfactory performance on the large textureless regions. We propose a simple but efficient method for stereo matching to tackle the problem, called area-based correlation and non-local attention network (Abc-Net). First, we exploit the area-based correlation to capture more local similarity in cost volume. The left-right features are sliced into various size patches along the channel dimension. Correlation maps are calculated between the left feature patches and corresponding traversed right patches and then pack them into a 4D area-based cost volume. Second, based on the hourglass module, we combined it with the non-local attention module as the 3D feature matching module, which exploits various spatial relationships and global information. The experiments show that (1) the area-based correlation can capture local similarity to increase accuracy on the large textureless region, (2) the improved 3D feature matching module can exploit global context information to further improve performance, (3) our method achieves competitive results on the SceneFlow, KITTI 2012, and KITTI 2015 datasets.

立体匹配在各种计算机视觉应用中起着至关重要的作用。成本量是衡量左右特征位置之间相似性的视差估计的关键部分。然而，大多数先前基于串联或像素相关的成本量构建缺乏局部相似性，导致在大的无纹理区域上的性能不令人满意。我们提出了一种简单但有效的立体匹配方法来解决这个问题，称为基于区域的相关性和非局部注意网络（Abc-Net）。首先，我们利用基于区域的相关性来捕获成本量的更多局部相似性。左右特征沿通道维度被切成不同大小的块。计算左侧特征块和相应遍历的右侧块之间的相关图，然后将它们打包成基于 4D 区域的成本量。其次，基于沙漏模块，我们将其与非局部注意力模块结合作为 3D 特征匹配模块，利用各种空间关系和全局信息。实验表明：（1）基于区域的相关性可以捕获局部相似性以提高大无纹理区域的准确性，（2）改进的 3D 特征匹配模块可以利用全局上下文信息进一步提高性能，（3）我们的方法实现SceneFlow、KITTI 2012 和 KITTI 2015 数据集上的竞争结果。我们将其与非局部注意力模块结合作为 3D 特征匹配模块，利用各种空间关系和全局信息。实验表明：（1）基于区域的相关性可以捕获局部相似性以提高大无纹理区域的准确性，（2）改进的 3D 特征匹配模块可以利用全局上下文信息进一步提高性能，（3）我们的方法实现SceneFlow、KITTI 2012 和 KITTI 2015 数据集上的竞争结果。我们将它与非局部注意力模块结合作为 3D 特征匹配模块，它利用了各种空间关系和全局信息。实验表明：（1）基于区域的相关性可以捕获局部相似性以提高大无纹理区域的准确性，（2）改进的 3D 特征匹配模块可以利用全局上下文信息进一步提高性能，（3）我们的方法实现SceneFlow、KITTI 2012 和 KITTI 2015 数据集上的竞争结果。