Learning semantic segmentation of large-scale point clouds with random sampling

Journal article

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. Comparative experiments show that our RandLA-Net can process 1 million points in a single pass with up to 200X faster than existing approaches. Moreover, extensive experiments on several large-scale point cloud datasets, including Semantic3D, SemanticKITTI, Toronto3D, S3DIS and NPM3D, demonstrate the state-of-the-art semantic segmentation performance of our RandLA-Net.

Authors: Hu, Q; Yang, B; Xie, L; Rosa, S; Guo, Y

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence
• Volume: 44
• Issue: 1
• Pages: 8338-8354
• Publication date: 2021-05-25
• Acceptance date: 2021-05-15
• DOI: 10.1109/TPAMI.2021.3083288
• EISSN: 1939-3539
• ISSN: 0162-8828
• Language: English
• Keywords: semantic segmentation; random sampling; large-scale point clouds; FFR; local feature aggregation