Metraipolis › archive › dc_08658cf90cda
HuLiGen: Human LiDAR Generation from Parametric Body Models — arXiv:2610.10196
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10196
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:47:54.957Z
- SHA-256 of the archived text
48c0b13a8481bb945534d7f093889d67155449fca37a84569406f3742c4a1261- Stable URL of this page
https://metraipolis.com/documento/dc_08658cf90cda
How to cite
HuLiGen: Human LiDAR Generation from Parametric Body Models — arXiv:2610.10196 — arXiv (en), https://arxiv.org/abs/2610.10196 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08658cf90cda (Metraipolis archive dc_08658cf90cda, sha256 48c0b13a8481bb945534d7f093889d67155449fca37a84569406f3742c4a1261)
BibTeX
@misc{dc08658cf90cda,
title = {HuLiGen: Human LiDAR Generation from Parametric Body Models — arXiv:2610.10196},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10196},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08658cf90cda; sha256 48c0b13a8481bb945534d7f093889d67155449fca37a84569406f3742c4a1261},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10196. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LiDAR point clouds of humans are extremely expensive to collect and annotate, thus represent a scarce resource that hinders the development of human analysis using this modality. To alleviate this scarcity, prior work relies on simulated human LiDAR, but such samples do not fully reflect the geometry and sensing characteristics of real observations. In contrast, we introduce HuLiGen, a generative model that generates human LiDAR point clouds from a parametric body model, using a point transformer trained with a flow-matching objective. We show that our generated point clouds are closer to the real capture distribution. Using HuLiGen to generate synthetic data, we propose a synthetic-only pretraining scheme for LiDAR-based HPE that achieves state-of-the-art performance, with even larger gains in low-annotation and low-data regimes, where MPJPE is reduced by up to 50%. Code, models and generated samples are available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.10196 — 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 2026-10-08T12:18:15.461Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).