ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909898873241600 |
|---|---|
| author | Luo, Ruifeng Liu, Zhengjie Cheng, Tianxiao Wang, Jie Wang, Tongjie Wei, Xingguang Wang, Haomin Li, YanPeng Chai, Fu Cheng, Fei Ye, Shenglong Wang, Wenhai Zhang, Yanting Qiao, Yu Zhang, Hongjie Zhao, Xianzhong |
| author_facet | Luo, Ruifeng Liu, Zhengjie Cheng, Tianxiao Wang, Jie Wang, Tongjie Wei, Xingguang Wang, Haomin Li, YanPeng Chai, Fu Cheng, Fei Ye, Shenglong Wang, Wenhai Zhang, Yanting Qiao, Yu Zhang, Hongjie Zhao, Xianzhong |
| contents | Recognizing symbols in architectural CAD drawings is critical for various advanced engineering applications. In this paper, we propose a novel CAD data annotation engine that leverages intrinsic attributes from systematically archived CAD drawings to automatically generate high-quality annotations, thus significantly reducing manual labeling efforts. Utilizing this engine, we construct ArchCAD-400K, a large-scale CAD dataset consisting of 413,062 chunks from 5538 highly standardized drawings, making it over 26 times larger than the largest existing CAD dataset. ArchCAD-400K boasts an extended drawing diversity and broader categories, offering line-grained annotations. Furthermore, we present a new baseline model for panoptic symbol spotting, termed Dual-Pathway Symbol Spotter (DPSS). It incorporates an adaptive fusion module to enhance primitive features with complementary image features, achieving state-of-the-art performance and enhanced robustness. Extensive experiments validate the effectiveness of DPSS, demonstrating the value of ArchCAD-400K and its potential to drive innovation in architectural design and construction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22346 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting Luo, Ruifeng Liu, Zhengjie Cheng, Tianxiao Wang, Jie Wang, Tongjie Wei, Xingguang Wang, Haomin Li, YanPeng Chai, Fu Cheng, Fei Ye, Shenglong Wang, Wenhai Zhang, Yanting Qiao, Yu Zhang, Hongjie Zhao, Xianzhong Computer Vision and Pattern Recognition Recognizing symbols in architectural CAD drawings is critical for various advanced engineering applications. In this paper, we propose a novel CAD data annotation engine that leverages intrinsic attributes from systematically archived CAD drawings to automatically generate high-quality annotations, thus significantly reducing manual labeling efforts. Utilizing this engine, we construct ArchCAD-400K, a large-scale CAD dataset consisting of 413,062 chunks from 5538 highly standardized drawings, making it over 26 times larger than the largest existing CAD dataset. ArchCAD-400K boasts an extended drawing diversity and broader categories, offering line-grained annotations. Furthermore, we present a new baseline model for panoptic symbol spotting, termed Dual-Pathway Symbol Spotter (DPSS). It incorporates an adaptive fusion module to enhance primitive features with complementary image features, achieving state-of-the-art performance and enhanced robustness. Extensive experiments validate the effectiveness of DPSS, demonstrating the value of ArchCAD-400K and its potential to drive innovation in architectural design and construction. |
| title | ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.22346 |