RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

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.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation S3DIS RandLA-Net mIoU 68.5 # 2
Mean IoU 70.0 # 23
mAcc 81.5 # 16
oAcc 87.1 # 26
Number of params 1.2M # 39
Semantic Segmentation Semantic3D RandLA-Net mIoU 77.4% # 4
oAcc 94.8 # 2
3D Semantic Segmentation SemanticKITTI RandLA-Net test mIoU 53.9% # 25
Semantic Segmentation Toronto-3D L002 RandLA-Net oAcc 88.4 # 3
mIoU 74.3 # 1