Metraipolis › archive › dc_59ffc3efdf5c
MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs — arXiv:2608.28669
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28669
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:59:39.171Z
- SHA-256 of the archived text
5d1b54ae276bb00d3217b9e761326870370eecbb1e7fe9794906a11437003d5a- Stable URL of this page
https://metraipolis.com/documento/dc_59ffc3efdf5c
How to cite
MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs — arXiv:2608.28669 — arXiv (en), https://arxiv.org/abs/2608.28669 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_59ffc3efdf5c (Metraipolis archive dc_59ffc3efdf5c, sha256 5d1b54ae276bb00d3217b9e761326870370eecbb1e7fe9794906a11437003d5a)
BibTeX
@misc{dc59ffc3efdf5c,
title = {MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs — arXiv:2608.28669},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28669},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_59ffc3efdf5c; sha256 5d1b54ae276bb00d3217b9e761326870370eecbb1e7fe9794906a11437003d5a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28669. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recovering an executable parametric CAD program from an observed object is fundamentally ambiguous, because the same final geometry can result from different construction procedures. We study this problem from four types of input: natural-language descriptions, rendered images, point clouds, and STEP/B-Rep geometry. MIRAGE-CAD maps each input to a shared construction representation and mediates program generation through an explicit construction-plan interface. The resulting Python CAD code is executed by an OpenCASCADE kernel to build the solid and export it as STEP. On 2,500 held-out queries per modality, the system achieves 55.4-70.0% build success and 52.3-66.2% STEP export success without retrieval at inference. Controlled comparisons show that strong reconstruction does not depend on expressing the construction representation as text: a decoder conditioned directly on the continuous representation also reconstructs strongly, while an exposure-matched plan-based decoder shows no detected material loss in per-part geometric fidelity. The explicit plan instead provides a readable and separately measurable intermediate representation whose agreement with the reference construction is informative about downstream execution success. Finally, we show that executable validity, geometric fidelity, and parametric responsiveness can diverge substantially and should therefore be evaluated separately. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-01 in cs.SE). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Programming Languages (cs.PL); Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.28669 — 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 2026-10-17T08:37:02.087Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).