DRINet++: Efficient Voxel-as-point Point Cloud Segmentation

Abstract

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.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
• RGCNN: Regularized Graph CNN for Point Cloud Segmentation
• The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
• (AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network
• Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion
• Learning Depth With Very Sparse Supervision