Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.10075 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914464946716672 |
|---|---|
| author | Gong, Shengjie Peng, Wenjie Chen, Hongyuan Zhang, Gangyu Hu, Yunqing Zhang, Huiyuan Huang, Shuangping Chen, Tianshui |
| author_facet | Gong, Shengjie Peng, Wenjie Chen, Hongyuan Zhang, Gangyu Hu, Yunqing Zhang, Huiyuan Huang, Shuangping Chen, Tianshui |
| contents | Text-to-CAD code generation is a long-horizon task that translates textual instructions into long sequences of interdependent operations. Existing methods typically decode text directly into executable code (e.g., bpy) without explicitly modeling assembly hierarchy or geometric constraints, which enlarges the search space, accumulates local errors, and often causes cascading failures in complex assemblies. To address this issue, we propose a hierarchical and geometry-aware graph as an intermediate representation. The graph models multi-level parts and components as nodes and encodes explicit geometric constraints as edges. Instead of mapping text directly to code, our framework first predicts structure and constraints, then conditions action sequencing and code generation, thereby improving geometric fidelity and constraint satisfaction. We further introduce a structure-aware progressive curriculum learning strategy that constructs graded tasks through controlled structural edits, explores the model's capability boundary, and synthesizes boundary examples for iterative training. In addition, we build a 12K dataset with instructions, decomposition graphs, action sequences, and bpy code, together with graph- and constraint-oriented evaluation metrics. Extensive experiments show that our method consistently outperforms existing approaches in both geometric fidelity and accurate satisfaction of geometric constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10075 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD Gong, Shengjie Peng, Wenjie Chen, Hongyuan Zhang, Gangyu Hu, Yunqing Zhang, Huiyuan Huang, Shuangping Chen, Tianshui Artificial Intelligence Text-to-CAD code generation is a long-horizon task that translates textual instructions into long sequences of interdependent operations. Existing methods typically decode text directly into executable code (e.g., bpy) without explicitly modeling assembly hierarchy or geometric constraints, which enlarges the search space, accumulates local errors, and often causes cascading failures in complex assemblies. To address this issue, we propose a hierarchical and geometry-aware graph as an intermediate representation. The graph models multi-level parts and components as nodes and encodes explicit geometric constraints as edges. Instead of mapping text directly to code, our framework first predicts structure and constraints, then conditions action sequencing and code generation, thereby improving geometric fidelity and constraint satisfaction. We further introduce a structure-aware progressive curriculum learning strategy that constructs graded tasks through controlled structural edits, explores the model's capability boundary, and synthesizes boundary examples for iterative training. In addition, we build a 12K dataset with instructions, decomposition graphs, action sequences, and bpy code, together with graph- and constraint-oriented evaluation metrics. Extensive experiments show that our method consistently outperforms existing approaches in both geometric fidelity and accurate satisfaction of geometric constraints. |
| title | Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.10075 |