CME-CAD：面向 CAD 代码生成的异构协同多专家强化学习
CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation
把 CAD 建模转成可执行的 CADQuery 代码生成，并用多专家协同的强化学习范式提升精度与可编辑性；对视觉研究者而言，它提供了从正交投影图到参数化三维模型的代码化重建路线，以及带精确尺寸标注与思维链的 17,299 条基准，可用于评测图像到可编辑三维结构的生成。
原文依据 Existing methods, such as 3D reconstruction from sketches, often produce non-editable, approximate models
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论计算机辅助设计（CAD）在工业设计中至关重要，但传统 CAD 建模与工作流的复杂性，为高精度、可编辑 CAD 模型的自动化生成带来了显著挑战。现有方法（例如从草图进行三维重建）往往产生不可编辑的近似模型，难以满足工业设计对精度与可编辑性的严苛要求。此外，对文本或图像输入的依赖通常需要大量人工标注，限制了其在工业场景中的可扩展性与适用性。为克服这些挑战，我们提出异构协同多专家强化学习（CME-CAD）范式，这是一种面向 CAD 代码生成的新型训练范式。该方法整合了这些模型互补的优势，促进协同学习，并提升模型生成准确、约束兼容且完全可编辑的 CAD 模型的能力。我们引入两阶段训练流程：多专家微调（MEFT）与多专家强化学习（MERL）。此外，我们提出 CADExpert，一个包含 17,299 个实例的开源基准，其中包括带精确尺寸标注的正交投影图、专家生成的思维链（CoT）过程、可执行的 CADQuery 代码以及渲染的三维模型。CADExpert 数据集已公开于 https://modelscope.cn/datasets/zhuofanChen/CADExpert。
英文原文摘要 1490 字符
Computer-Aided Design (CAD) is essential in industrial design, but the complexity of traditional CAD modeling and workflows presents significant challenges for automating the generation of high-precision, editable CAD models. Existing methods, such as 3D reconstruction from sketches, often produce non-editable, approximate models that fall short of meeting the stringent requirements for precision and editability in industrial design. Moreover, the reliance on text or image-based inputs often requires significant manual annotation, limiting their scalability and applicability in industrial settings. To overcome these challenges, we propose the Heterogeneous Collaborative Multi-Expert Reinforcement Learning (CME-CAD) paradigm, a novel training paradigm for CAD code generation. Our approach integrates the complementary strengths of these models, facilitating collaborative learning and improving the model's ability to generate accurate, constraint-compatible, and fully editable CAD models. We introduce a two-stage training process: Multi-Expert Fine-Tuning (MEFT), and Multi-Expert Reinforcement Learning (MERL). Additionally, we present CADExpert, an open-source benchmark consisting of 17,299 instances, including orthographic projections with precise dimension annotations, expert-generated Chain-of-Thought (CoT) processes, executable CADQuery code, and rendered 3D models. The CADExpert dataset is publicly available at https://modelscope.cn/datasets/zhuofanChen/CADExpert.