arXiv：cs.AI· Qingwang Zhang, Jiahao Li, Xiangdong Zhou·· 18 小时前
HiCAD：通过协同多任务对齐与空间感知强化学习生成参数化 CAD 模型
Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning
AI 导读
研究团队提出 HiCAD 两阶段框架，可直接将手绘草图和文本描述等多层次人类意图映射为可执行的参数化 CAD 代码，无需预设目标 CAD 模型存在。团队同时构建了首个对齐手绘草图、文本描述与参数化 CAD 代码的大规模数据集 HiCAD，该框架包含协同多任务对齐与空间感知强化学习两个阶段。实验表明该方法在多项任务上显著优于现有基线，论文已被 ICML 2026 接收。
正文
Abstract:Parametric Computer-Aided-Design (CAD) modeling from human intent remains challenging, particularly during the conceptual design stage, where design goals are expressed through incomplete and unstructured modalities (e.g., hand-drawn sketches and textual descriptions). In this work, we rethink the human intent-to-CAD pipeline and propose a unified method that directly maps multi-level human intents to executable codes, without assuming the prior existence of target CAD models. To support our study, we construct HiCAD, the first large-scale dataset aligning hand-drawn sketches, textual descriptions, and parametric CAD codes. Based on this, we introduce HiCAD, a two-stage framework comprising Cooperative Multi-Task Alignment to bridge the representational gap between heterogeneous inputs, and Spatial-Aware Reinforcement Learning to enforce geometric and topological consistency. Extensive experiments demonstrate that our method significantly outperforms existing baselines across multiple tasks, validating its effectiveness and robustness in transforming heterogeneous human intents into high-fidelity parametric CAD models. Our project page: this https URL.
| Comments: | Accepted at ICML 2026. Published in Proceedings of Machine Learning Research (PMLR), Volume 306 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.15681 [cs.CV] |
| (or arXiv:2610.15681v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15681 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Proceedings of the 43rd International Conference on Machine Learning (ICML), PMLR 306:156956-156970, 2026 |
Submission history
From: Qingwang Zhang [view email]
[v1]
Sun, 11 Oct 2026 15:05:49 UTC (7,712 KB)
来源：arXiv：cs.AI · arxiv.org