Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mismatches. In this paper, the Motif Cha}nnel Attention Stereo Matching Network (MoCha-Stereo) is designed to address this problem. We provide the Motif Channel Correlation Volume (MCCV) to determine more accurate edge matching costs. MCCV is achieved by projecting motif channels, which capture common geometric structures in feature channels, onto feature maps and cost volumes. In addition, edge variations in %potential feature channels of the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation. REMP integrates the frequency information of typical channel features from the reconstruction error. MoCha-Stereo ranks 1st on the KITTI-2015 and KITTI-2012 Reflective leaderboards. Our structure also shows excellent performance in Multi-View Stereo. Code is avaliable at https://github.com/ZYangChen/MoCha-Stereo.

翻译：基于学习的立体匹配技术已取得显著进展。然而，现有方法在特征通道生成过程中不可避免地会丢失几何结构信息，导致边缘细节失配。本文设计了基元通道注意力立体匹配网络（MoCha-Stereo）以解决该问题。我们提出基元通道相关体积（MCCV）来确定更精确的边缘匹配代价。MCCV通过将捕获特征通道中常见几何结构的基元通道投影至特征图与代价体积来实现。此外，重建误差图中潜在特征通道的边缘变化也会影响细节匹配，因此我们进一步提出重建误差基元惩罚（REMP）模块来优化全分辨率视差估计。REMP融合了来自重建误差的典型通道特征的频率信息。MoCha-Stereo在KITTI-2015和KITTI-2012反射排行榜上均位列第一。我们的结构在多视图立体任务中也展现出优异性能。代码发布于https://github.com/ZYangChen/MoCha-Stereo。