cs.CVNov 18, 2026

DrawScore: Evaluating Generated CAD Models against Engineering Drawings

Authors: Haorui Chen, Shiteng Lu, Zhanyu Guo, Zaixi Li, Yunhe Ni, Yaosong Du, Yichen Xiang, Xiande Huang, 

Organizations: University of Electronic Science and Technology of China · De Artificial Intelligence Technology Co., Ltd · University of Hong Kong

Abstract

Automatic 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)(k+q)-th power of its size, where kk is the dimension of the integration domain and qq 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.

Figures & tables

Explore similar work

CardsList
  1. Text-to-CAD Evaluation with CADTests

    May 8, 2026Dimitrios Mallis, Marco Wang, Ahmet Serdar Karadeniz +3Text-to-CAD GenerationAutomated Evaluation

  2. Blueprint2CAD: Benchmarking Foundation Models on Engineering Drawing-to-CAD Render Correspondence

    Nov 2, 2026Alexander Valverde, Danny Xie-Li, Zhichao Wang +1VLM EvaluationCross-View Image Matching