Metraipolis › archive › dc_4915596b87cb

SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting — arXiv:2609.29836

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29836
License (as archived)
CC0-1.0
Archived
2026-10-08T06:44:37.415Z
SHA-256 of the archived text
c3fcc17877ef14183a01c183f3cefcab8de0c12a0e8b278e1ce51ceea4da43e6
Stable URL of this page
https://metraipolis.com/documento/dc_4915596b87cb

How to cite

SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting — arXiv:2609.29836 — arXiv (en), https://arxiv.org/abs/2609.29836 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4915596b87cb (Metraipolis archive dc_4915596b87cb, sha256 c3fcc17877ef14183a01c183f3cefcab8de0c12a0e8b278e1ce51ceea4da43e6)
BibTeX
@misc{dc4915596b87cb,
  title = {SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting — arXiv:2609.29836},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29836},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4915596b87cb; sha256 c3fcc17877ef14183a01c183f3cefcab8de0c12a0e8b278e1ce51ceea4da43e6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29836. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While 2D Vision Foundation Models offer a pathway to automate 3D semantic pseudo-labelling, translating these priors into robust 3D representations typically requires complex heuristics or multi-model ensembles. We introduce SplatLabel, an automated pipeline that leverages a 4D Gaussian representation to extract LiDAR segmentation with predictive confidence, as well as semantic occupancy grids at arbitrary voxel resolutions. At its core, SplatLabel handles dynamic environments through an explicit temporal manifold that models the trajectories and lifespans of individual 3D primitives. This allows the system to accurately track moving actors and strictly define when objects appear and disappear, completely eliminating the need for pre-annotated 3D bounding boxes. To robustly support this dynamic tracking, the representation is grounded by structural and semantic priors: we guide scene geometry in unobserved regions by integrating 360-degree LiDAR via virtual depth maps, and rather than relying on domain-specific prompt engineering, we directly distill continuous soft probabilities from 2D models to inherently resolve semantic ambiguities over time and space. Finally, to accurately reflect the real-world trade-off between precision and recall, we reframe pseudo-label evaluation as a selective classification task using a generalized risk-recall metric. Experiments on SemanticKITTI demonstrate that SplatLabel consistently outperforms state-of-the-art baselines across multiple recall levels, establishing a highly robust framework for both 3D LiDAR segmentation and occupancy prediction.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.29836 — 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 2026-10-08T06:09:29.890Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).