# A Data-Centric Approach to 3D Semantic Segmentation of Railway Scenes

Source: [A Data-Centric Approach to 3D Semantic Segmentation of Railway Scenes](<https://www.sota2.com/research/paper/68fa783f1e209131cea77646>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:34:18.624Z

Authors: Nicolas M\\"unger, Max Peter Ronecker, Xavier Diaz, Michael Karner, Daniel Watzenig, Jan Skaloud

Published: 2025-04-25T09:46:31.000Z

## Abstract

LiDAR-based semantic segmentation is critical for autonomous trains, requiring accurate predictions across varying distances. This paper introduces two targeted data augmentation methods designed to improve segmentation performance on the railway-specific OSDaR23 dataset. The person instance pasting method enhances segmentation of pedestrians at distant ranges by injecting realistic variations into the dataset. The track sparsification method redistributes point density in LiDAR scans, improving track segmentation at far distances with minimal impact on close-range accuracy. Both methods are evaluated using a state-of-the-art 3D semantic segmentation network, demonstrating significant improvements in distant-range performance while maintaining robustness in close-range predictions. We establish the first 3D semantic segmentation benchmark for OSDaR23, demonstrating the potential of data-centric approaches to address railway-specific challenges in autonomous train perception.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.18213>)

[PDF](<https://arxiv.org/pdf/2504.18213.pdf>)