期刊
IEEE ACCESS
卷 9, 期 -, 页码 19651-19658出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3050540
关键词
Stereo matching; depth estimation computer vision; traditional method; neural network
资金
- National Key Research and Development Program of China [2018YFB0204301]
- General Program of National Natural Science Foundation of China [81973244]
- Science and Technology Program Projects of Shenzhen [JCYJ20170818110101726]
BSDCNet is a real-time stereo matching network that utilizes traditional methods and neural networks to generate two different cost volumes, with faster speed and more accurate stereo matching results compared to other fast stereo networks.
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., 36x than GC-Net, 16x than PSMNet, and 72x 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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据