Part segmentation method of point cloud considering optimal allocation and optimal mask
In order to enhance the generalization ability of the network and improve the accuracy of part segmentation,this paper proposed a method for part segmentation of point cloud considering the optimal allocation and the optimal mask. Firstly,the optimal allocation between two point clouds was defined ac-cording to Earth Mover's Distance. Then the point cloud was grouped by the Farthest Point Sampling,the significance of each point in the grouping is calculated,and the optimal mask of the point cloud was deter-mined by the ball query to preserve the semantic information of the original point cloud. Finally,the neigh-borhood of a point with high significance in one cloud was replaced by the neighborhood of a point with low significance in another cloud,so as to achieve hybrid enhancement between point clouds. In this paper,the data was verified on ShapeNet data set,and the method was enhanced to PointNet,PointNet++and DGCNN models. The mIoU increased from 83.7％,85.1％ and 85.1％ to 85.1％,86.3％ and 86.0％ respectively,effectively improving the effect of component segmentation.
data augmentationpoint cloudpart segmentationsaliency
万方数据
维普
