# Online Segmentation of LiDAR Sequences: Dataset and Algorithm

Source: [Online Segmentation of LiDAR Sequences: Dataset and Algorithm](<https://www.sota2.com/research/paper/68fa6d1a1e209131cea37c34>)

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

Data updated: 2025-12-22T09:34:33.810Z

Authors: Romain Loiseau, Mathieu Aubry, Lo\\"ic Landrieu

Published: 2022-06-16T14:08:58.000Z

## Abstract

Roof-mounted spinning LiDAR sensors are widely used by autonomous vehicles. However, most semantic datasets and algorithms used for LiDAR sequence segmentation operate on $360^\\circ$ frames, causing an acquisition latency incompatible with real-time applications. To address this issue, we first introduce HelixNet, a $10$ billion point dataset with fine-grained labels, timestamps, and sensor rotation information necessary to accurately assess the real-time readiness of segmentation algorithms. Second, we propose Helix4D, a compact and efficient spatio-temporal transformer architecture specifically designed for rotating LiDAR sequences. Helix4D operates on acquisition slices corresponding to a fraction of a full sensor rotation, significantly reducing the total latency. Helix4D reaches accuracy on par with the best segmentation algorithms on HelixNet and SemanticKITTI with a reduction of over $5\\times$ in terms of latency and $50\\times$ in model size. The code and data are available at: https://romainloiseau.fr/helixnet

## 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/2206.08194>)

[PDF](<https://arxiv.org/pdf/2206.08194.pdf>)
