PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis
This work addresses the challenge of improving feature representations for 3D point cloud tasks, which is important for applications like robotics and autonomous driving, but it is incremental as it builds on existing strategies.
The paper tackles the problem of 3D point cloud analysis by proposing PRA-Net, a framework that unifies intra-region context and inter-region relation learning, achieving state-of-the-art results on benchmarks for shape classification, keypoint estimation, and part segmentation.
Learning intra-region contexts and inter-region relations are two effective strategies to strengthen feature representations for point cloud analysis. However, unifying the two strategies for point cloud representation is not fully emphasized in existing methods. To this end, we propose a novel framework named Point Relation-Aware Network (PRA-Net), which is composed of an Intra-region Structure Learning (ISL) module and an Inter-region Relation Learning (IRL) module. The ISL module can dynamically integrate the local structural information into the point features, while the IRL module captures inter-region relations adaptively and efficiently via a differentiable region partition scheme and a representative point-based strategy. Extensive experiments on several 3D benchmarks covering shape classification, keypoint estimation, and part segmentation have verified the effectiveness and the generalization ability of PRA-Net. Code will be available at https://github.com/XiwuChen/PRA-Net .