· 2020
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
- 2,031citations
- 2020year
Short summary
RandLA-Net, a neural network using random point sampling and a local feature aggregation module, achieves efficient semantic segmentation of large-scale 3D point clouds, processing 1 million points up to 200x faster than prior methods.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces RandLA-Net, a lightweight neural network for direct per-point semantic segmentation of large-scale 3D point clouds.
- Utilizes random point sampling, a computationally efficient alternative to complex sampling techniques.
- Incorporates a local feature aggregation module to retain geometric details lost by random sampling.
- Achieves processing speeds up to 200x faster for 1 million points compared to existing methods.
- Surpasses state-of-the-art performance on Semantic3D and SemanticKITTI benchmarks.
AI-generated from the title and abstract; the full text is not read.
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.
The authors' abstract, as published at the source., 2020 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computational Mechanics
Computational MechanicsEngineering