aiqbench analysis
This research introduces CADKnitter, a generative AI framework that uses diffusion models guided by geometric cues to compose multi-part 3D designs from text prompts and existing geometry. By releasing the KnitCAD dataset with over 310,000 samples, the work addresses critical gaps in semantic constraints and assembly compatibility for practical manufacturing applications. The method demonstrates significant performance gains over current baselines, marking a step toward automating complex CAD workflows previously limited to single-part generation.
CADKnitter: Compositional CAD Generation from Text and Geometry Guidance
arXiv:2512.11199v2 Announce Type: replace-cross Abstract: Computer-aided design (CAD) defines 3D models as compact, precise, and editable representations, making it directly useful for several fields. Recently, CAD generation has been gaining more attention in both the research community and industry. Crafting CAD models has long been a painstaking and time-intensive task, demanding both precision and expertise from designers. Prior works have achieved early success in single-part CAD generation, which is not well-suited for real-world applications, as multiple parts need to be assembled under semantic constraints and geometric compatibility. In this paper, we propose CADKnitter, a compositional CAD generation framework with geometric-guiding cues to steer diffusion sampling. CADKnitter is able to generate a complementary CAD part that follows both the geometric constraints of the given CAD model and the semantic constraints of the desired design text prompt. We also curate a dataset, so-called KnitCAD, containing over 310,000 samples of CAD models, along with textual prompts and assembly metadata that provide semantic and geometric constraints. Intensive experiments demonstrate that our proposed method outperforms other state-of-the-art baselines by a clear margin. Our project page is available at https://cadknitter.github.io/.
Abstract:Computer-aided design (CAD) defines 3D models as compact, precise, and editable representations, making it directly useful for several fields. Recently, CAD generation has been gaining more attention in both the research community and industry. Crafting CAD models has long been a painstaking and time-intensive task, demanding both precision and expertise from designers. Prior works have achieved early success in single-part CAD generation, which is not well-suited for real-world applications, as multiple parts need to be assembled under semantic constraints and geometric compatibility. In this paper, we propose CADKnitter, a compositional CAD generation framework with geometric-guiding cues to steer diffusion sampling. CADKnitter is able to generate a complementary CAD part that follows both the geometric constraints of the given CAD model and the semantic constraints of the desired design text prompt. We also curate a dataset, so-called KnitCAD, containing over 310,000 samples of CAD models, along with textual prompts and assembly metadata that provide semantic and geometric constraints. Intensive experiments demonstrate that our proposed method outperforms other state-of-the-art baselines by a clear margin. Our project page is available at this https URL.
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2512.11199 [cs.CV]
(or arXiv:2512.11199v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2512.11199 Focus to learn more arXiv-issued DOI via DataCite
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.
Full text under the publisher's open licence · 279 words
Related coverage
The Plan, Not the Decoder: Diagnosing and Repairing Compositional Failure in Reasoning-Augmented Text-to-Image Generation
arXiv · Aug 25, 2026
TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward
arXiv · Jul 28, 2026
Why do models task game?
AI Alignment Forum · Aug 6, 2026
Best Free Image Generators on Hugging Face Right Now!
KDnuggets · Jun 9, 2026