Metraipolis › archive › dc_46ef164d1406
Vision2CAD: A Visual Agent Harness for Explicit Geometry Referencing and Localization in Parametric CAD Modeling — arXiv:2609.22688
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22688
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T21:59:15.388Z
- SHA-256 of the archived text
7083aaa04fd6a4e15b8ad54787df5f40089af1c5ff7b924aac19123dbff3f036- Stable URL of this page
https://metraipolis.com/documento/dc_46ef164d1406
How to cite
Vision2CAD: A Visual Agent Harness for Explicit Geometry Referencing and Localization in Parametric CAD Modeling — arXiv:2609.22688 — arXiv (en), https://arxiv.org/abs/2609.22688 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46ef164d1406 (Metraipolis archive dc_46ef164d1406, sha256 7083aaa04fd6a4e15b8ad54787df5f40089af1c5ff7b924aac19123dbff3f036)
BibTeX
@misc{dc46ef164d1406,
title = {Vision2CAD: A Visual Agent Harness for Explicit Geometry Referencing and Localization in Parametric CAD Modeling — arXiv:2609.22688},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22688},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46ef164d1406; sha256 7083aaa04fd6a4e15b8ad54787df5f40089af1c5ff7b924aac19123dbff3f036},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22688. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generating parametric CAD models requires accurate geometry and stable feature dependencies. Existing methods face challenges in selecting geometric references, interpreting sketch-plane local coordinates, and establishing sketch constraints to projected external geometry. We present Vision2CAD, a visual agent harness that combines vision-language model (VLM) reasoning with deterministic CAD kernel operations. An ID-based interface supports explicit geometry selection, a local-coordinate bridge converts view coordinates into sketch coordinates, and projected-edge localization supports external sketch constraints. These mechanisms establish feature dependencies within the supported modeling operations and constraint types. We also introduce the Geometry Explicit Reference Dataset (GERD), which aligned commands, geometry states and IDs at every modeling step. On GERD-EVL and a DeepCAD test subset, Vision2CAD improves mIoU by 11.1\% and 5.6\% and reduces Chamfer distance by 17.3\% and 41.8\%, respectively. Parameter-editing experiments and ablation studies further proved the preservation of parametric dependencies. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.22688 — 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 2026-10-09T21:45:20.808Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).