RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
arXiv:1911.11236
Abstract
We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Extensive experiments show that our RandLA-Net can process 1 million points in a single pass with up to 200X faster than existing approaches. Moreover, our RandLA-Net clearly surpasses state-of-the-art approaches for semantic segmentation on two large-scale benchmarks Semantic3D and SemanticKITTI.
arXiv commentCVPR 2020 Oral. Code and data are available at: https://github.com/QingyongHu/RandLA-Net
References in corpus (16)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Joint 2D-3D-Semantic Data for Indoor Scene Understanding
- Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
- PointConv: Deep Convolutional Networks on 3D Point Clouds
- Relation-Shape Convolutional Neural Network for Point Cloud Analysis
- Concrete Autoencoders for Differentiable Feature Selection and Reconstruction
- SPLATNet: Sparse Lattice Networks for Point Cloud Processing
- Recurrent Slice Networks for 3D Segmentation of Point Clouds
- Deep Learning for 3D Point Clouds: A Survey
- Classification of Point Cloud Scenes with Multiscale Voxel Deep Network
- Tangent Convolutions for Dense Prediction in 3D
- A-CNN: Annularly Convolutional Neural Networks on Point Clouds
- Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
- LSANet: Feature Learning on Point Sets by Local Spatial Aware Layer
- PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval
- Octree guided CNN with Spherical Kernels for 3D Point Clouds