# LVCA-Net: Lightweight LiDAR Semantic Segmentation for Advanced Sensor-Based Perception in Autonomous Transportation Systems

## TL;DR

This paper introduces LVCA-Net, a lightweight framework for LiDAR-based 3D scene understanding in autonomous vehicles, achieving high accuracy and real-time performance.

## Contribution

LVCA-Net introduces a novel lightweight architecture for LiDAR semantic segmentation with improved spatial consistency and real-time efficiency.

## Key findings

- LVCA-Net achieves 67.17% mIoU and 91.79% overall accuracy on the SemanticKITTI benchmark.
- The model reaches 77.1% mIoU on the nuScenes benchmark while maintaining real-time inference efficiency.

## Abstract

Reliable 3D scene understanding is a fundamental requirement for intelligent machines in autonomous transportation systems, as on-board perception must remain accurate and stable across diverse environments and sensing conditions. However, LiDAR point clouds acquired in real traffic scenes are often sparse and irregular, and they exhibit heterogeneous sampling patterns that hinder consistent and fine-grained semantic interpretation. To address these challenges, this paper proposes LVCA-Net, a lightweight voxel–coordinate attention framework designed for efficient LiDAR-based 3D semantic segmentation in autonomous driving scenarios. The architecture integrates (i) an anisotropic depthwise residual module for direction-aware geometric feature extraction, (ii) a hierarchical LiteDown–LiteUp pathway for multi-scale feature fusion, and (iii) a Coordinate-Guided Sparse Semantic Module that enhances spatial consistency in a cylindrical voxel space while maintaining computational sparsity. Experiments on the SemanticKITTI and nuScenes benchmarks demonstrate that LVCA-Net achieves 67.17% mean Intersection over Union (mIoU) and 91.79% overall accuracy on SemanticKITTI, as well as 77.1% mIoU on nuScenes, while maintaining real-time inference efficiency. These results indicate that LVCA-Net delivers scalable and robust 3D scene understanding with high semantic precision for LiDAR-only perception, making it well suited for deployment in autonomous vehicles and other safety-critical intelligent systems.