TerraSeg: Self-Supervised Ground Segmentation for Any LiDAR

TL;DR

TerraSeg is a self-supervised, domain-agnostic LiDAR ground segmentation model trained on a large, diverse dataset, achieving state-of-the-art results without manual labels.

Contribution

Introduces TerraSeg, the first self-supervised ground segmentation model for LiDAR, trained on OmniLiDAR, a large-scale, diverse dataset, with a novel PseudoLabeler module.

Findings

Achieves state-of-the-art results on nuScenes, SemanticKITTI, and Waymo datasets.

Operates in real-time without manual annotations.

Demonstrates high generalization across diverse sensor types.

Abstract

LiDAR perception is fundamental to robotics, enabling machines to understand their environment in 3D. A crucial task for LiDAR-based scene understanding and navigation is ground segmentation. However, existing methods are either handcrafted for specific sensor configurations or rely on costly per-point manual labels, severely limiting their generalization and scalability. To overcome this, we introduce TerraSeg, the first self-supervised, domain-agnostic model for LiDAR ground segmentation. We train TerraSeg on OmniLiDAR, a unified large-scale dataset that aggregates and standardizes data from 12 major public benchmarks. Spanning almost 22 million raw scans across 15 distinct sensor models, OmniLiDAR provides unprecedented diversity for learning a highly generalizable ground model. To supervise training without human annotations, we propose PseudoLabeler, a novel module that generates high-quality ground and non-ground labels through self-supervised per-scan runtime optimization. Extensive evaluations demonstrate that, despite using no manual labels, TerraSeg achieves state-of-the-art results on nuScenes, SemanticKITTI, and Waymo Perception while delivering real-time performance. Our code and model weights are publicly available.