Metraipolis › archive › dc_2202113edbb2

CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning — arXiv:2610.04262

Source: arXiv
Original: https://arxiv.org/abs/2610.04262
License (as archived): CC0-1.0
Archived: 2026-10-06T05:24:25.345Z
SHA-256 of the archived text: 8b195ddc2c741cfb4ea04cf45703df2afa8516d25cd9aee828ee0cdabc29a713
Stable URL of this page: https://metraipolis.com/documento/dc_2202113edbb2

How to cite

CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning — arXiv:2610.04262 — arXiv, https://arxiv.org/abs/2610.04262 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2202113edbb2 (Metraipolis archive dc_2202113edbb2, sha256 8b195ddc2c741cfb4ea04cf45703df2afa8516d25cd9aee828ee0cdabc29a713)

BibTeX

@misc{dc2202113edbb2,
  title = {CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning — arXiv:2610.04262},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04262},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2202113edbb2; sha256 8b195ddc2c741cfb4ea04cf45703df2afa8516d25cd9aee828ee0cdabc29a713},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04262. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reconstructing editable parametric CAD models from a single-view image is of great practical value for modern manufacturing, yet remains challenging due to incomplete geometric observations and complex inter-part relationships. To address it, we propose CADForge, an agentic framework that progressively converts a single image into CadQuery programs. CADForge decomposes an object into CAD-meaningful components and performs explicit geometric reasoning for each component, a process that first identifies CAD-relevant constraints and then translates them into precise modeling parameters through mathematical code. The inferred parameters then drive component-wise synthesis of executable CadQuery programs, with a review agent evaluating the resulting geometry and providing targeted feedback for iterative refinement. To further improve robustness and efficiency, CADForge incorporates a failure-guided toolkit construction mechanism to distill accumulated experience into tools, and maintains a compact parametric CAD memory for retrieving modeling context on demand. Experiments on diverse single- and multi-part objects show that CADForge consistently outperforms existing baselines in reconstruction fidelity and perceptual quality, demonstrating an effective approach to accurate single-view CAD reconstruction.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.04262 — 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 2026-10-06T05:24:05.447Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).