Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling
This addresses the problem of computational inefficiency in point cloud segmentation for applications like autonomous driving and robotics, though it is incremental as it builds on existing neural architectures.
They tackled efficient semantic segmentation of large-scale 3D point clouds by introducing RandLA-Net, which uses random sampling and a local feature aggregation module, achieving state-of-the-art performance and processing 1 million points up to 200x faster than existing approaches.
We study the problem of efficient semantic segmentation of 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. Comparative experiments show that our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches. Moreover, extensive experiments on five large-scale point cloud datasets, including Semantic3D, SemanticKITTI, Toronto3D, NPM3D and S3DIS, demonstrate the state-of-the-art semantic segmentation performance of our RandLA-Net.