AI Paper Atlas

Research map / Point clouds / Segmentation and detection

TerraSeg: Self-Supervised Ground Segmentation for Any LiDAR

Ted Lentsch, Santiago Montiel-Marín, Holger Caesar, Dariu M. Gavrila

CVPR 2026 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add pre-processing (0.5% low-height quantile filter) to PseudoLabeler (ablation)PseudoLabeler · nuScenes valmIoU: 79.40 -> 86.38Improved
add pre-processing to PseudoLabeler (ablation)PseudoLabeler · Waymo Perception valmIoU: 85.00 -> 85.47Improved
add pillar-based post-processing to PseudoLabeler (ablation)PseudoLabeler · SemanticKITTI valmIoU: 83.82 -> 91.97Improved
add pillar-based post-processing to PseudoLabeler (ablation)PseudoLabeler · nuScenes valmIoU: 86.38 -> 90.63Improved
increase recovery threshold tau from 0.05 to 0.20 (ablation)PseudoLabeler post-processing · avg mIoU, pillar 0.50 mmIoU: 91.85 -> 89.76Hurt
change pillar size from 0.50 m to 0.25 m or 1.00 m (ablation)PseudoLabeler post-processing · avg mIoU, tau 0.05mIoU: 91.85 -> 91.08 / 90.63Hurt
train on pseudo-labels from many LiDARs instead of single-dataset supervised GndNetTerraSeg-B vs GndNet · Waymo Perception valmIoU: 61.83 -> 94.40Improved
use manual labels (supervised oracle) instead of pseudo-labelsTerraSeg-B · nuScenes valmIoU: 92.47 -> 95.31Improved
use larger TerraSeg-B instead of TerraSeg-STerraSeg · nuScenes valmIoU: 91.45 -> 92.47Improved
distill PseudoLabeler into TerraSeg-B modelPseudoLabeler · nuScenes valmIoU: 90.63 -> 92.47Improved
non-flat terrain (sigma > 0.40 m) vs flatTerraSeg-B · nuScenes valmIoU: 93.12 -> 87.81Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy