IPC-Net: Incomplete point cloud classification network based on data augmentation and similarity measurement

Existing point cloud classification researches are usually conducted on datasets with complete structure and clear semantics. However, in real point cloud scenes, the occlusion and truncation may destroy the completeness of objects affecting the classification performance. To solve this problem, we propose an incomplete point cloud classification network (IPC-Net) with data augmentation and similarity measurement. The proposed network learns the feature representation of incomplete point clouds and the semantic differences compared to the complete ones for classification. Specifically, IPC-Net adopts a random erasing-based data augmentation to deal with incomplete point clouds. IPC-Net also introduces an auxiliary loss function weighted by attention scores to measure the similarity between the incomplete and the complete point clouds. Extensive experiments verify that IPC-Net has the ability to classify incomplete point clouds and significantly improves the robustness of point cloud classification under different completeness.

Automated summary

Existing point cloud classification researches are usually conducted on complete and semantically clear datasets. However, in real point cloud scenes, occlusion and truncation can affect classification performance by destroying object completeness. To address this issue, we propose an incomplete point cloud classification network (IPC-Net) that utilizes data augmentation and similarity measurement. IPC-Net learns feature representation of incomplete point clouds and semantic differences compared to complete ones for improved classification. Experimental results validate the ability of IPC-Net to classify incomplete point clouds and enhance the robustness of point cloud classification under varying completeness levels.