CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908601137758208 |
|---|---|
| author | Niu, Ke Chen, Zhuofan Yu, Haiyang Chen, Yuwen Fu, Teng Zhao, Mengyang Li, Bin Xue, Xiangyang |
| author_facet | Niu, Ke Chen, Zhuofan Yu, Haiyang Chen, Yuwen Fu, Teng Zhao, Mengyang Li, Bin Xue, Xiangyang |
| contents | Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing. Orthographic projection reasoning underpins the entire CAD workflow, encompassing design, manufacturing, and simulation. However, prevailing deep-learning approaches employ standard 3D reconstruction pipelines as an alternative, which often introduce imprecise dimensions and limit the parametric editability required for CAD workflows. Recently, some researchers adopt vision-language models (VLMs), particularly supervised fine-tuning (SFT), to tackle CAD-related challenges. SFT shows promise but often devolves into pattern memorization, yielding poor out-of-distribution performance on complex reasoning tasks. To address these gaps, we introduce CReFT-CAD, a two-stage fine-tuning paradigm that first employs a curriculum-driven reinforcement learning stage with difficulty-aware rewards to build reasoning ability steadily, and then applies supervised post-tuning to hone instruction following and semantic extraction. Complementing this, we release TriView2CAD, the first large-scale, open-source benchmark for orthographic projection reasoning, comprising 200,000 synthetic and 3,000 real-world orthographic projections with precise dimension annotations and six interoperable data modalities. We benchmark leading VLMs on orthographic projection reasoning and demonstrate that CReFT-CAD substantially improves reasoning accuracy and out-of-distribution generalizability in real-world scenarios, offering valuable insights for advancing CAD reasoning research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00568 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning Niu, Ke Chen, Zhuofan Yu, Haiyang Chen, Yuwen Fu, Teng Zhao, Mengyang Li, Bin Xue, Xiangyang Computer Vision and Pattern Recognition Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing. Orthographic projection reasoning underpins the entire CAD workflow, encompassing design, manufacturing, and simulation. However, prevailing deep-learning approaches employ standard 3D reconstruction pipelines as an alternative, which often introduce imprecise dimensions and limit the parametric editability required for CAD workflows. Recently, some researchers adopt vision-language models (VLMs), particularly supervised fine-tuning (SFT), to tackle CAD-related challenges. SFT shows promise but often devolves into pattern memorization, yielding poor out-of-distribution performance on complex reasoning tasks. To address these gaps, we introduce CReFT-CAD, a two-stage fine-tuning paradigm that first employs a curriculum-driven reinforcement learning stage with difficulty-aware rewards to build reasoning ability steadily, and then applies supervised post-tuning to hone instruction following and semantic extraction. Complementing this, we release TriView2CAD, the first large-scale, open-source benchmark for orthographic projection reasoning, comprising 200,000 synthetic and 3,000 real-world orthographic projections with precise dimension annotations and six interoperable data modalities. We benchmark leading VLMs on orthographic projection reasoning and demonstrate that CReFT-CAD substantially improves reasoning accuracy and out-of-distribution generalizability in real-world scenarios, offering valuable insights for advancing CAD reasoning research. |
| title | CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.00568 |