We introduce Double Cost Volume Stereo Matching Network(DCVSMNet) which is a novel architecture characterised by by two small upper (group-wise) and lower (norm correlation) cost volumes. Each cost volume is processed separately, and a coupling module is proposed to fuse the geometry information extracted from the upper and lower cost volumes. DCVSMNet is a fast stereo matching network with a 67 ms inference time and strong generalization ability which can produce competitive results compared to state-of-the-art methods. The results on several bench mark datasets show that DCVSMNet achieves better accuracy than methods such as CGI-Stereo and BGNet at the cost of greater inference time.

翻译：我们提出双代价体立体匹配网络（DCVSMNet），这是一种以两个小型上层（分组）和下层（范数相关）代价体为特征的新型架构。每个代价体被独立处理，并设计了一个耦合模块来融合从上下层代价体中提取的几何信息。DCVSMNet是一种快速立体匹配网络，推理时间为67毫秒，具有较强的泛化能力，能够与最先进的方法产生竞争性的结果。在多个基准数据集上的结果表明，DCVSMNet在牺牲更大推理时间的情况下，相比CGI-Stereo和BGNet等方法实现了更高的精度。