titleDrawScore: Evaluating Generated CAD Models against Engineering Drawings
authorsHaorui Chen, Shiteng Lu, Zhanyu Guo, Zaixi Li, Yunhe Ni, Yaosong Du, Yichen Xiang, Xiande Huang, Rui Huang
date2026-11-18
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.24681
upvotes5 (Hugging Face Daily Papers, 2026-11-21)
linksabs pdf hf code
cite
abstractAutomatic CAD generation is commonly evaluated with volumetric IoU, Chamfer Distance, and surface F-score, which barely penalize local errors that occupy only a small fraction of a part's volume or surface area, such as a misplaced hole or a slot on the wrong face, even though such errors are critical to manufacturing. We formalize these metrics in a unified integral form and show that the weight of a local error decays as the (k+q)-th power of its size, where k is the dimension of the integration domain and q is determined by the penalty function. Guided by this analysis, we propose DrawScore, which projects both models into three orthographic views with visible and hidden lines, as in engineering drawings, and applies a saturating penalty along the projected curves, so that the weight of a local error decays only linearly. Controlled experiments confirm the predicted decay orders, and on outputs of existing CAD generation agents, DrawScore exposes errors in outputs that IoU rates as nearly perfect. DrawScore further improves generation as a reinforcement learning reward and, for CAD generation from engineering drawings, serves as a test-time verifier without 3D ground truth or an additional reward model. Our code is available at https://github.com/UESTC-Simon/DrawScore.

bibtex

@misc{chen2026drawscore,
  title={DrawScore: Evaluating Generated CAD Models against Engineering Drawings},
  author={Haorui Chen and Shiteng Lu and Zhanyu Guo and Zaixi Li and Yunhe Ni and Yaosong Du and Yichen Xiang and Xiande Huang and Rui Huang},
  year={2026},
  eprint={2611.24681},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.24681}
}