Metraipolis › archive › dc_e2240e69ebd4
Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers — arXiv:2610.00855
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00855
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T19:11:48.732Z
- SHA-256 of the archived text
28b0d292a721db242d2160fd9302e011ad8de9019a61920a33d6fb1e3208942f- Stable URL of this page
https://metraipolis.com/documento/dc_e2240e69ebd4
How to cite
Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers — arXiv:2610.00855 — arXiv (en), https://arxiv.org/abs/2610.00855 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e2240e69ebd4 (Metraipolis archive dc_e2240e69ebd4, sha256 28b0d292a721db242d2160fd9302e011ad8de9019a61920a33d6fb1e3208942f)
BibTeX
@misc{dce2240e69ebd4,
title = {Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers — arXiv:2610.00855},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00855},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e2240e69ebd4; sha256 28b0d292a721db242d2160fd9302e011ad8de9019a61920a33d6fb1e3208942f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00855. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Accurate 3D semantic perception is critical for safe autonomous navigation. However, supervised LiDAR segmentation remains tied to closed taxonomies and to the cost of point-wise manual annotation. Open-vocabulary methods avoid that cost by projecting the output of 2D vision-language models onto LiDAR and distilling it into a 3D network. These methods rely almost exclusively on voxel-based sparse convolutions, and point transformers have so far been limited to indoor environments, where 3D data is dense and bounded. We present Lang3DSeg, which establishes a point transformer as the backbone for annotation-free open-vocabulary segmentation of outdoor 3D LiDAR, and is trained from scratch without geometric pre-training. This training paradigm necessitates addressing the inherent noise in 2D-to-3D label projections; specifically, naive projection often suffers from depth ambiguity, where points behind an object are erroneously assigned its semantic label. We therefore composite masks using an explicit class-priority rule and truncate each projected instance at the first gap in its depth distribution, correcting the projection error directly rather than averaging it over registered sequences. Lang3DSeg achieves 52.8% mIoU on nuScenes validation and 41.4% on SemanticKITTI, the highest among published annotation-free methods on both benchmarks. Every 3D semantic segmentation is on a single LiDAR sweep, and inference operates in real-time without running vision-language models. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.00855 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T17:37:36.705Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).