Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
This work addresses point cloud semantic segmentation for 3D scene understanding, presenting an incremental improvement through hierarchical graph-based interactions.
The paper tackles 3D semantic scene labeling by proposing a hierarchical point-edge interaction network that explores semantic relations between points and contextual neighbors through edges, achieving decent experimental results on several datasets.
We achieve 3D semantic scene labeling by exploring semantic relation between each point and its contextual neighbors through edges. Besides an encoder-decoder branch for predicting point labels, we construct an edge branch to hierarchically integrate point features and generate edge features. To incorporate point features in the edge branch, we establish a hierarchical graph framework, where the graph is initialized from a coarse layer and gradually enriched along the point decoding process. For each edge in the final graph, we predict a label to indicate the semantic consistency of the two connected points to enhance point prediction. At different layers, edge features are also fed into the corresponding point module to integrate contextual information for message passing enhancement in local regions. The two branches interact with each other and cooperate in segmentation. Decent experimental results on several 3D semantic labeling datasets demonstrate the effectiveness of our work.