基于全融合网络的三维点云语义分割

为提高室内场景的点云语义分割精度，设计了一个全融合点云语义分割网络。网络由特征编码模块、渐进式特征解码模块、多尺度特征解码模块、特征融合模块和语义分割头部组成。特征编码模块采用逆密度加权卷积作为特征编码器对点云数据进行逐级特征编码，提取点云数据的多尺度特征；然后通过渐进式特征解码器对高层语义特征进行逐层解码，得到点云的渐进式解码特征。同时，多尺度特征解码器对提取的点云多尺度特征分别进行特征解码，得到点云多尺度解码特征。最后将渐进式解码特征与多尺度解码特征融合，输入语义分割头部实现点云的语义分割。全融合网络增强了网络特征提取能力的鲁棒性，实验结果也验证了该网络的有效性。

Semantic segmentation of 3D point cloud based on all fusion network

In order to improve the accuracy of point cloud semantic segmentation in indoor scenes, an all fusion network for semantic segmentation of 3D point clound is proposed. The network consists of a feature encoding module, a progressive feature decoding module, a multi-scale feature decoding module, a feature fusion module, and a semantic segmentation header. The feature encoding module uses inverse density weighted convolution as the feature encoder to perform hierarchical feature encoding on point cloud, so as to extract multi-scale features of the point cloud. Then, the progressive feature decoder is used to decode high-level semantic features layer by layer to obtain the point cloud progressive decoding feature. In the same pair, the multi-scale feature decoder performs feature decoding on the extracted multi-scale features to obtain multi-scale decoding features of the point cloud. Finally, the progressive decoding feature is fused with the multi-scale decoding feature, then semantic segmentation header is introduced to realize the point cloud semantic segmentation. The all fusion network robustly enhances the feature extraction ability of the network, and the experimental results also verify the effectiveness of the method.