Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation

Abstract

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.

Accepted by ICCV 2019

References in corpus (5)

• ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
• SPLATNet: Sparse Lattice Networks for Point Cloud Processing
• Recurrent Slice Networks for 3D Segmentation of Point Clouds
• Tangent Convolutions for Dense Prediction in 3D
• PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames

Cited by in corpus (4)

• RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
• PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
• PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
• 3D Point Cloud Descriptors in Hand-crafted and Deep Learning Age: State-of-the-Art