Metraipolis › archive › dc_dcf1510bdf7e
Task-Adaptive Grounded 3D-Programmers Using 2D VLMs — arXiv:2610.02021
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.02021
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:15:50.046Z
- SHA-256 of the archived text
4e5e5f9bdf964d58035528f598793ee17e1a7f9d674d2bc7f179ad83b76a935d- Stable URL of this page
https://metraipolis.com/documento/dc_dcf1510bdf7e
How to cite
Task-Adaptive Grounded 3D-Programmers Using 2D VLMs — arXiv:2610.02021 — arXiv (en), https://arxiv.org/abs/2610.02021 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcf1510bdf7e (Metraipolis archive dc_dcf1510bdf7e, sha256 4e5e5f9bdf964d58035528f598793ee17e1a7f9d674d2bc7f179ad83b76a935d)
BibTeX
@misc{dcdcf1510bdf7e,
title = {Task-Adaptive Grounded 3D-Programmers Using 2D VLMs — arXiv:2610.02021},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.02021},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcf1510bdf7e; sha256 4e5e5f9bdf964d58035528f598793ee17e1a7f9d674d2bc7f179ad83b76a935d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02021. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent vision-language models (VLMs) exhibit remarkable generalization and reasoning abilities, yet 3D understanding in these models is limited by data scale, training diversity, and reasoning capacity. Instead of naively extending these models into 3D, we take a different approach: we enable powerful 2D VLMs to operate reliably in 3D by introducing 3D grounding and iterative feedback loops with two novel concepts: Canonical Coordinate Framing (CCF) and Task-Adaptive Feedback (TAF). CCF serves as a unified visual representation that anchors both inputs and outputs to a shared Euclidean coordinate system, solving common challenges in 3D grounding such as axis ambiguity, inconsistent metric scale, and floating references. Complementary to this structured framing of the 3D inputs, TAF closes the reasoning loop with task-adaptive dynamic feedback that enables 2D VLMs to perform varied open-vocabulary tasks within their native visual context. Building on this foundation, we introduce 3D-Prog, a 3D understanding, reasoning, and generation framework that jointly employs the capabilities of CCF and TAF together with powerful VLMs. Without requiring any retraining, 3D-Prog performs open-vocabulary 3D understanding, manipulation, and generation across both object-level and scene-level tasks. Our experiments show that the joint use of CCF and TAF transforms 2D VLMs into geometry-aware 3D programmers, achieving consistent, interpretable, and high-quality results across diverse 3D tasks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.02021 — 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 2026-10-06T10:21:28.236Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).