Metraipolis › archive › dc_5bceea67323e

OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection — arXiv:2610.03015

Source
arXiv
Original
https://arxiv.org/abs/2610.03015
License (as archived)
CC0-1.0
Archived
2026-10-05T22:50:24.133Z
SHA-256 of the archived text
59273733f7a471b3080b796d86ba5cd9acf89631684debbb0be346ce0434e052
Stable URL of this page
https://metraipolis.com/documento/dc_5bceea67323e

How to cite

OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection — arXiv:2610.03015 — arXiv, https://arxiv.org/abs/2610.03015 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5bceea67323e (Metraipolis archive dc_5bceea67323e, sha256 59273733f7a471b3080b796d86ba5cd9acf89631684debbb0be346ce0434e052)
BibTeX
@misc{dc5bceea67323e,
  title = {OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection — arXiv:2610.03015},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03015},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5bceea67323e; sha256 59273733f7a471b3080b796d86ba5cd9acf89631684debbb0be346ce0434e052},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03015. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate 3D detection is essential for mobile embodied agents, while Vision Foundation Models (VFMs) offer transferable visual and geometric priors. Yet existing VFM-based 3D detectors rely on narrow-view monocular images or discrete perspective views, limiting coherent surround perception; equirectangular projection (ERP) instead encodes a continuous 360 scene in a single image. Direct transfer remains difficult because ERP organizes geometry and visual information differently, making object-relevant cues hard to model, localize, and preserve. We propose OmniAct3D, a framework that adapts perspective-trained VFM detectors to ERP while preserving transferable VFM priors. To resolve geometric mismatch, the ERP-Ray Geometry Adapter (ERGA-Ray) models spherical viewing rays and periodic spatial structure. To localize evidence in scene-wide context, the Visual-Action Reasoning Chain (VARC) grounds each hypothesis in relevant panoramic evidence and converts it into a structured geometric action. To recover local cues lost under fixed token budgets, the Appearance-Guided Heading Expert (AGHE) re-encodes object regions at higher resolution for heading estimation. Experiments show that OmniAct3D improves over the previous best 3D detector by 2.96 NDS points on Spheriverse and over the unadapted VFM baseline by 24.87 mAP points on PanoMMOcc. With target-specific geometry adaptation, VARC retains 95--98% of the same-configuration mAP, indicating reusable object-level 3D reasoning across sensing configurations. The source code will be made publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.03015 — 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 2026-10-05T22:45:55.818Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).