Point cloud registration is a fundamental step for many tasks. In this paper, we propose a neural network named DetarNet to decouple the translation $t$ and rotation $R$, so as to overcome the performance degradation due to their mutual interference in point cloud registration. First, a Siamese Network based Progressive and Coherent Feature Drift (PCFD) module is proposed to align the source and target points in high-dimensional feature space, and accurately recover translation from the alignment process. Then we propose a Consensus Encoding Unit (CEU) to construct more distinguishable features for a set of putative correspondences. After that, a Spatial and Channel Attention (SCA) block is adopted to build a classification network for finding good correspondences. Finally, the rotation is obtained by Singular Value Decomposition (SVD). In this way, the proposed network decouples the estimation of translation and rotation, resulting in better performance for both of them. Experimental results demonstrate that the proposed DetarNet improves registration performance on both indoor and outdoor scenes. Our code will be available in \url{https://github.com/ZhiChen902/DetarNet}.
翻译:云点登记是许多任务的基本步骤。 在本文中, 我们提议建立一个名为 DetarNet 的神经网络, 以拆分翻译美元和旋转美元, 以克服由于在点云登记中相互干扰而导致的性能退化。 首先, 提出一个基于Siamse网络的进步和相交地貌地貌( PCFD) 模块, 以协调高维特征空间的源点和目标点, 并准确地从校对过程中恢复翻译。 然后, 我们提议建立一个共识编码股( CEU), 为一套模拟通信建立更清晰的功能。 之后, 将采用一个空间和频道注意块, 以建立用于查找好通信的分类网络。 最后, 由 Singultural value Decommation ( SVD) 获得这种旋转。 这样, 拟议的网络将翻译和旋转的估计分解出来, 从而改善两者的性能。 实验结果显示, 拟议的DetarNet 将改善室内和室外的登记性能。 我们的代码将在 url{https://github. com/ Zhen2/Zhichen.