论文标题
ASAP-NET：注意力和结构感知点云序列分割
ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation
论文作者
论文摘要
点云的最新作品表明，Mulit-Frame时空建模通过利用跨帧信息优于单帧版本。在本文中，我们进一步改善了时空点云特征学习，并使用一个称为ASAP的灵活模块考虑了跨帧的注意力和结构信息，我们发现这是在动态点云中成功分割的两个重要因素。首先，我们的ASAP模块包含一个新颖的专注时间嵌入层，以复发方式融合跨帧相对信息的本地特征。其次，提出了一种有效的时空相关方法，以利用更多的局部结构来嵌入，同时实施时间一致性并降低计算复杂性。最后，我们显示了针对点云序列分割的不同骨干网络所建议的ASAP模块的概括能力。我们的ASAP-NET（Backbone Plus ASAP模块）优于Synthia和Semantickitti数据集（+3.4至+15.2 MIOU指向具有不同骨架）的基准和以前的方法。代码在https://github.com/intrepidchw/asap-net上可用
Recent works of point clouds show that mulit-frame spatio-temporal modeling outperforms single-frame versions by utilizing cross-frame information. In this paper, we further improve spatio-temporal point cloud feature learning with a flexible module called ASAP considering both attention and structure information across frames, which we find as two important factors for successful segmentation in dynamic point clouds. Firstly, our ASAP module contains a novel attentive temporal embedding layer to fuse the relatively informative local features across frames in a recurrent fashion. Secondly, an efficient spatio-temporal correlation method is proposed to exploit more local structure for embedding, meanwhile enforcing temporal consistency and reducing computation complexity. Finally, we show the generalization ability of the proposed ASAP module with different backbone networks for point cloud sequence segmentation. Our ASAP-Net (backbone plus ASAP module) outperforms baselines and previous methods on both Synthia and SemanticKITTI datasets (+3.4 to +15.2 mIoU points with different backbones). Code is availabe at https://github.com/intrepidChw/ASAP-Net
