M2S-RoAD: Multi-Modal Semantic Segmentation for Road Damage Using Camera and LiDAR Data

Tzu-Yun Tseng, Hongyu Lyu, Josephine Li, Julie Stephany Berrio, Mao Shan +1 more
4/14/2025
cs.CV

No official code found. Best implementation: chinitaberrio/M2S-RoAD (9 stars, last commit 2026-02-27).

Abstract

Road damage can create safety and comfort challenges for both human drivers and autonomous vehicles (AVs). This damage is particularly prevalent in rural areas due to less frequent surveying and maintenance of roads. Automated detection of pavement deterioration can be used as an input to AVs and driver assistance systems to improve road safety. Current research in this field has predominantly focused on urban environments driven largely by public datasets, while rural areas have received significantly less attention. This paper introduces M2S-RoAD, a dataset for the semantic segmentation of different classes of road damage. M2S-RoAD was collected in various towns across New South Wales, Australia, and labelled for semantic segmentation to identify nine distinct types of road damage. This dataset will be released upon the acceptance of the paper.

View on arXivView PDF

Code Implementations(1)

chinitaberrio/M2S-RoADCommunity100%

Multi-Modal Semantic Segmentation for Road Damage Using Camera and LiDAR Data

90PythonSep 18, 20247 months ago

Similar Papers

TD-RD: A Top-Down Benchmark with Real-Time Framework for Road Damage Detection

85% match2025

Solving Scene Understanding for Autonomous Navigation in Unstructured Environments

84% match2025

A Performance Increment Strategy for Semantic Segmentation of Low-Resolution Images from Damaged Roads

83% match1 repo22024

RDD4D: 4D Attention-Guided Road Damage Detection And Classification

83% match1 repo62025

PaveSync: A Unified and Comprehensive Dataset for Pavement Distress Analysis and Classification

82% match2025

Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving

82% match1 repo462026

Cite this paper

@article{tseng2025msroad,
  title  = {M2S-RoAD: Multi-Modal Semantic Segmentation for Road Damage Using Camera and LiDAR Data},
  author = {Tzu-Yun Tseng and Hongyu Lyu and Josephine Li and Julie Stephany Berrio and Mao Shan and Stewart Worrall},
  year   = {2025},
  eprint = {2504.10123},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.10123v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.10123.svg)](https://codeofpaper.com/paper/2504.10123)

Discussion