Metraipolis › archive › dc_6c2afa7f6ed2

AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks — arXiv:2609.38864

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38864
License (as archived)
CC0-1.0
Archived
2026-10-07T14:45:36.700Z
SHA-256 of the archived text
e7f8a75b65d24200ff839b4667ccf92178813ab56208c3d4a1be7dd707e797b3
Stable URL of this page
https://metraipolis.com/documento/dc_6c2afa7f6ed2

How to cite

AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks — arXiv:2609.38864 — arXiv (en), https://arxiv.org/abs/2609.38864 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6c2afa7f6ed2 (Metraipolis archive dc_6c2afa7f6ed2, sha256 e7f8a75b65d24200ff839b4667ccf92178813ab56208c3d4a1be7dd707e797b3)
BibTeX
@misc{dc6c2afa7f6ed2,
  title = {AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks — arXiv:2609.38864},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38864},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6c2afa7f6ed2; sha256 e7f8a75b65d24200ff839b4667ccf92178813ab56208c3d4a1be7dd707e797b3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38864. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Embodied tasks demand accurate, flexible, and semantically rich 3D scene representations. 3D semantic occupancy is well suited to this requirement, as it can model holistic 3D spaces by encoding geometric occupancy along with semantic categories. However, existing occupancy prediction methods struggle to meet practical deployment requirements, such as adapting to varying computing budgets, sensor setups, and observation views. In this paper, we propose a point-based Adaptive 3D Occupancy Prediction method, called AdaOcc, tailored for embodied scenarios. To accommodate heterogeneous sensor inputs, AdaOcc uses an adaptive geometry-guided dual-branch encoder that can support RGB images in various numbers of views with (estimated) depth maps or LiDAR scans. AdaOcc represents occupied regions via sparse semantic points trained with a progressive query learning strategy, allowing the prediction computational budget to be flexibly adjusted through query point numbers and decoder layers. To facilitate high-fidelity geometric modeling for lightweight point-based occupancy learning, we further propose a novel containment loss that regularizes predicted points to reside within valid occupied regions. Extensive experiments show that our method achieves a new state-of-the-art on Occ-ScanNet with considerable performance improvements over previous methods. Moreover, our framework demonstrates strong practical applicability as an adaptive 3D perception module in real-world embodied systems.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.38864 — 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 2026-10-07T14:19:00.629Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).