Bidirectional Stereo Matching Network With Double Cost Volumes

Abstract

In stereo matching, the high-quality cost volume is the key to improve the matching accuracy. Current stereo matching networks only use traditional methods or neural networks to generate one or more cost volumes. They do not consider combining different matching cost computation methods to improve the quality of cost volume. Therefore, we propose BSDCNet, a real-time stereo matching network consisting of two main modules: Double Matching Cost Computation and Bidirectional Cost Aggregation Network. The Double Matching Cost Computation module generates two different cost volumes through traditional methods and neural networks. The Bidirectional Cost Aggregation Network is a two-branch structure, which can aggregate the above two cost volumes with different network depths. Finally, we also design a feature fusion module (FFM) to fuse the two-branch features and use the result for disparity estimation. Our network only uses 3D cost volumes and two-dimensional convolutions. Thus it is much faster than state-of-the-art stereo networks (e.g., 36× than GC-Net, 16× than PSMNet, and 72× than GA-Net). Meanwhile, according to the KITTI official website, our network is more accurate than other fast stereo networks (e.g., Fast DS-CS, RTSNet, and DispNetC), demonstrating that our network can generate a real-time and accurate stereo matching result.