LEST: Large-Scale LiDAR Semantic Segmentation With Deployment-Friendly Transformer Architecture

Large-scale LiDAR-based point cloud semantic segmentation is a critical challenge for autonomous driving perception. Most state-of-the-art LiDAR semantic segmentation methods rely on complex operators, such as sparse 3D convolutions or KdTree structures, which hinder their deployment on modern embed...

Full description

Saved in:
Bibliographic Details
Main Authors: Chuanyu Luo, Nuo Cheng, Sikun Ma, Han Li, Xiaohan Li, Shengguang Lei, Pu Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10904146/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Large-scale LiDAR-based point cloud semantic segmentation is a critical challenge for autonomous driving perception. Most state-of-the-art LiDAR semantic segmentation methods rely on complex operators, such as sparse 3D convolutions or KdTree structures, which hinder their deployment on modern embedded devices. While transformer architectures have gained prominence in natural language processing (NLP) and 2D computer vision, their application to large-scale point cloud semantic segmentation remains limited. In this paper, we introduce LEST (LiDAR sEmantic Segmentation architecture with Transformer), a novel framework built entirely on simple operators. LEST incorporates two key innovations: a Space Filling Curve (SFC) grouping strategy and a DIStance-based COsine (DISCO) linear transformer. Experimental results demonstrate that our model achieves competitive performance on the nuScenes semantic segmentation validation set and the SemanticKITTI test set, while maintaining a deployment-friendly design.
ISSN:2169-3536