CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915976201633792 |
|---|---|
| author | Pyatov, Vladislav Bobrovskikh, Gleb Galochkin, Saveliy Boldyrev, Nikita Voynov, Oleg Filippov, Alexander Ferrer, Gonzalo Wonka, Peter Burnaev, Evgeny |
| author_facet | Pyatov, Vladislav Bobrovskikh, Gleb Galochkin, Saveliy Boldyrev, Nikita Voynov, Oleg Filippov, Alexander Ferrer, Gonzalo Wonka, Peter Burnaev, Evgeny |
| contents | We introduce CADFS, a data-centric framework that enables large vision-language models to generate complex CAD design histories. Existing generative CAD systems are restricted to sketch-extrude operations due to simplified representations and limited datasets. We address this by introducing a FeatureScript-based representation and constructing a dataset of 450k real-world CAD models spanning 15 modeling operations. We obtain the dataset via a new pipeline that reconstructs clean, executable FeatureScript programs and provides multimodal annotations. Fine-tuning a VLM on this representation yields state-of-the-art results in text-conditioned CAD generation and image-based reconstruction, producing more accurate, diverse, and feature-rich designs than prior frameworks. Ablations show that each individual component of our framework, i.e., the FeatureScript representation, the extended operation set, and representation-aligned textual descriptions, significantly improves performance. Our framework substantially broadens the complexity and realism achievable in generative CAD. The CADFS framework and the new dataset are available at https://voyleg.github.io/cadfs/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01925 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models Pyatov, Vladislav Bobrovskikh, Gleb Galochkin, Saveliy Boldyrev, Nikita Voynov, Oleg Filippov, Alexander Ferrer, Gonzalo Wonka, Peter Burnaev, Evgeny Computer Vision and Pattern Recognition Graphics We introduce CADFS, a data-centric framework that enables large vision-language models to generate complex CAD design histories. Existing generative CAD systems are restricted to sketch-extrude operations due to simplified representations and limited datasets. We address this by introducing a FeatureScript-based representation and constructing a dataset of 450k real-world CAD models spanning 15 modeling operations. We obtain the dataset via a new pipeline that reconstructs clean, executable FeatureScript programs and provides multimodal annotations. Fine-tuning a VLM on this representation yields state-of-the-art results in text-conditioned CAD generation and image-based reconstruction, producing more accurate, diverse, and feature-rich designs than prior frameworks. Ablations show that each individual component of our framework, i.e., the FeatureScript representation, the extended operation set, and representation-aligned textual descriptions, significantly improves performance. Our framework substantially broadens the complexity and realism achievable in generative CAD. The CADFS framework and the new dataset are available at https://voyleg.github.io/cadfs/. |
| title | CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2605.01925 |