DRINet++: Efficient Voxel-as-point Point Cloud Segmentation
This addresses efficiency and memory issues in outdoor point cloud segmentation for applications like autonomous driving, though it appears incremental as an extension of DRINet.
The paper tackles the problem of balancing performance, efficiency, and memory consumption in point cloud semantic segmentation by proposing DRINet++, which enhances sparsity and geometric properties using a voxel-as-point principle. It achieves state-of-the-art results on SemanticKITTI and Nuscenes datasets while running faster and using less memory.
Recently, many approaches have been proposed through single or multiple representations to improve the performance of point cloud semantic segmentation. However, these works do not maintain a good balance among performance, efficiency, and memory consumption. To address these issues, we propose DRINet++ that extends DRINet by enhancing the sparsity and geometric properties of a point cloud with a voxel-as-point principle. To improve efficiency and performance, DRINet++ mainly consists of two modules: Sparse Feature Encoder and Sparse Geometry Feature Enhancement. The Sparse Feature Encoder extracts the local context information for each point, and the Sparse Geometry Feature Enhancement enhances the geometric properties of a sparse point cloud via multi-scale sparse projection and attentive multi-scale fusion. In addition, we propose deep sparse supervision in the training phase to help convergence and alleviate the memory consumption problem. Our DRINet++ achieves state-of-the-art outdoor point cloud segmentation on both SemanticKITTI and Nuscenes datasets while running significantly faster and consuming less memory.