NLCA-Net: a non-local context attention network for stereo matching
Zhibo Rao, Mingyi He, Yuchao Dai, Zhidong Zhu, Bo Li, Renjie He · APSIPA Transactions on Signal and Information Processing · 2020
NLCA-Net: a non-local context attention network for stereo matching zhibo rao, 1 mingyi he, 1 yuchao dai, 1 zhidong zhu, 1 bo li 1 and renjie he 1,2 Accurate disparity prediction is a hot spot in computer vision, and how to efficiently exploit contextual information is the key to improve the performance.In this paper, we propose a simple yet effective non-local context attention network to exploit the global context information by using attention mechanisms and semantic information for stereo matching.First, we develop a 2D geometry feature learning module to get a more discriminative representation by taking advantage of multi-scale features and form them into the variance-based cost volume.Then, we construct a non-local attention matching module by using the nonlocal block and hierarchical 3D convolutions, which can effectively regularize the cost volume and capture the global contextual information.Finally, we adopt a geometry refinement module to refine the disparity map to further improve the performance.Moreover, we add the warping loss function to help the model learn the matching rule of the non-occluded region.Our experiments show that (1) our approach achieves competitive results on KITTI and SceneFlow datasets in the end-point error and the fraction of erroneous pixels (D 1 ); (2) our proposed method particularly has superior performance in the reflective regions and occluded areas.