待翻译：MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs
AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.28669v1 Announce Type: new Abstract: 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.
AI 服务暂时不可用，以下为来源正文，待恢复后补全翻译。
--> [Submitted on 24 Aug 2026] Title:MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs View a PDF of the paper titled MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs, by Jizong Zhan View PDF HTML (experimental) Abstract: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. Comments: 64 pages, 5 figures, 20 tables, 7 appendices. Code, evaluation scripts and run reports: this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV); Programming Languages (cs.PL); Software Engineering (cs.SE) ACM classes: I.3.5; I.2.6; I.2.7 Cite as: arXiv:2608.28669 [cs.CV] (or arXiv:2608.28669v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.28669 arXiv-issued DOI via DataCite (pending registration) Submission history From: Jizong Zhan [view email] [v1] Mon, 24 Aug 2026 09:45:36 UTC (1,040 KB) Full-text links: Access Paper: View a PDF of the paper titled MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs, by Jizong Zhan View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV new | recent | 2026-08 Change to browse by: cs cs.PL cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)