UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decomposition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ghilotti, Filippo, Brucker, Samuel, Saidy, Nahku, Matteucci, Matteo, Bijelic, Mario, Heide, Felix
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908904333508608
author Ghilotti, Filippo
Brucker, Samuel
Saidy, Nahku
Matteucci, Matteo
Bijelic, Mario
Heide, Felix
author_facet Ghilotti, Filippo
Brucker, Samuel
Saidy, Nahku
Matteucci, Matteo
Bijelic, Mario
Heide, Felix
contents Unlabeled LiDAR logs, in autonomous driving applications, are inherently a gold mine of dense 3D geometry hiding in plain sight - yet they are almost useless without human labels, highlighting a dominant cost barrier for autonomous-perception research. In this work we tackle this bottleneck by leveraging temporal-geometric consistency across LiDAR sweeps to lift and fuse cues from text and 2D vision foundation models directly into 3D, without any manual input. We introduce an unsupervised multi-modal pseudo-labeling method relying on strong geometric priors learned from temporally accumulated LiDAR maps, alongside with a novel iterative update rule that enforces joint geometric-semantic consistency, and vice-versa detecting moving objects from inconsistencies. Our method simultaneously produces 3D semantic labels, 3D bounding boxes, and dense LiDAR scans, demonstrating robust generalization across three datasets. We experimentally validate that our method compares favorably to existing semantic segmentation and object detection pseudo-labeling methods, which often require additional manual supervision. We confirm that even a small fraction of our geometrically consistent, densified LiDAR improves depth prediction by 51.5% and 22.0% MAE in the 80-150 and 150-250 meters range, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05105
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decomposition
Ghilotti, Filippo
Brucker, Samuel
Saidy, Nahku
Matteucci, Matteo
Bijelic, Mario
Heide, Felix
Computer Vision and Pattern Recognition
Unlabeled LiDAR logs, in autonomous driving applications, are inherently a gold mine of dense 3D geometry hiding in plain sight - yet they are almost useless without human labels, highlighting a dominant cost barrier for autonomous-perception research. In this work we tackle this bottleneck by leveraging temporal-geometric consistency across LiDAR sweeps to lift and fuse cues from text and 2D vision foundation models directly into 3D, without any manual input. We introduce an unsupervised multi-modal pseudo-labeling method relying on strong geometric priors learned from temporally accumulated LiDAR maps, alongside with a novel iterative update rule that enforces joint geometric-semantic consistency, and vice-versa detecting moving objects from inconsistencies. Our method simultaneously produces 3D semantic labels, 3D bounding boxes, and dense LiDAR scans, demonstrating robust generalization across three datasets. We experimentally validate that our method compares favorably to existing semantic segmentation and object detection pseudo-labeling methods, which often require additional manual supervision. We confirm that even a small fraction of our geometrically consistent, densified LiDAR improves depth prediction by 51.5% and 22.0% MAE in the 80-150 and 150-250 meters range, respectively.
title UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decomposition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.05105