Pattern Recognition Letters ( IF 3.9 ) Pub Date : 2020-03-16 , DOI: 10.1016/j.patrec.2020.03.021 Heng Zhou , Zhijun Fang , Yongbin Gao , Bo Huang , Cengsi Zhong , Ruoxi Shang
3D scene parsing has always been a hot topic and point clouds are efficient data format to represent scenes. The semantic segmentation of point clouds is critical to the 3D scene, which is a challenging problem due to the unordered structure of point clouds. The max-pooling operation is typically used to obtain the order invariant features, while the point-wise features are destroyed after the max-pooling operation. In this paper, we propose a feature fusion network that fuses point-wise features and local features by attention mechanism to compensate for the loss caused by max-pooling operation. By incorporating point-wise features into local features, the point-wise variation is preserved to obtain a refined segmentation accuracy, and the attention mechanism is used to measure the importance of the point-wise features and local features for each 3D point. Extensive experiments show that our method achieves better performances than other prestigious methods.
中文翻译:
基于注意力机制的特征融合网络的点云3D语义分割
3D场景解析一直是热门话题,而点云是表示场景的高效数据格式。点云的语义分割对于3D场景至关重要,由于点云的无序结构,这是一个具有挑战性的问题。max-pooling操作通常用于获取阶数不变特征,而max-pooling操作后将破坏逐点特征。在本文中,我们提出了一种特征融合网络,该网络通过注意机制将点状特征和局部特征融合在一起,以补偿最大池操作所造成的损失。通过将逐点特征合并到局部特征中,可以保留逐点变化以获得精确的分割精度,注意机制用于衡量每个3D点的逐点特征和局部特征的重要性。大量的实验表明,我们的方法比其他著名方法具有更好的性能。