Timezone: »

 
Spotlight
Learning Superpoint Graph Cut for 3D Instance Segmentation
Le Hui · Linghua Tang · Yaqi Shen · Jin Xie · Jian Yang

Wed Dec 07 09:00 AM -- 11:00 AM (PST) @

3D instance segmentation is a challenging task due to the complex local geometric structures of objects in point clouds. In this paper, we propose a learning-based superpoint graph cut method that explicitly learns the local geometric structures of the point cloud for 3D instance segmentation. Specifically, we first oversegment the raw point clouds into superpoints and construct the superpoint graph. Then, we propose an edge score prediction network to predict the edge scores of the superpoint graph, where the similarity vectors of two adjacent nodes learned through cross-graph attention in the coordinate and feature spaces are used for regressing edge scores. By forcing two adjacent nodes of the same instance to be close to the instance center in the coordinate and feature spaces, we formulate a geometry-aware edge loss to train the edge score prediction network. Finally, we develop a superpoint graph cut network that employs the learned edge scores and the predicted semantic classes of nodes to generate instances, where bilateral graph attention is proposed to extract discriminative features on both the coordinate and feature spaces for predicting semantic labels and scores of instances. Extensive experiments on two challenging datasets, ScanNet v2 and S3DIS, show that our method achieves new state-of-the-art performance on 3D instance segmentation.

Author Information

Le Hui (Nanjing University of Science and Technology)
Linghua Tang (Nanjing University of Science and Technology)
Yaqi Shen (Nanjing University of Science and Technology)
Jin Xie (Department of Computer Science, Nanjing University of Science and Technology)
Jian Yang (Nanjing University of Science and Technology)

More from the Same Authors