ConCAD：具有双粒度奖励的约束感知图像到CAD生成
ConCAD: Constraint-Aware Image-to-CAD Generation with Dual-Granularity Rewards
- Tsinghua University, Shenzhen International Graduate School（清华大学深圳国际研究生院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
ConCAD提出一种约束感知的图像到CAD生成框架，通过GRPO优化并采用代码级约束与执行级几何双粒度奖励，结合G-CSR评估，在DeepCAD和Zero2CAD上实现更优的IoU、倒角距离和约束满足率。
AI中文摘要：
图像到CAD生成旨在寻求可执行的参数化程序，以恢复参考对象的几何形状和设计意图。现有系统通常通过有效性和形状重叠来评估，尽管两个体积相似的实体可能编码不同的CAD关系。我们引入了ConCAD，这是一种约束感知的图像到CAD框架，通过组相对策略优化（GRPO）进行优化，并在两个互补的粒度上提供奖励：代码级约束奖励和执行级几何奖励。这种互补设计消除了结构不同但体积相似的形状之间的歧义，同时确保有效的3D几何形状。为了验证这些奖励能够恢复几何形状和设计意图，我们引入了B-rep几何约束满足率（G-CSR），它从边界表示中分析性地提取和评估几何约束。在DeepCAD和Zero2CAD上的实验表明，ConCAD在IoU和倒角距离上优于竞争基线，同时在G-CSR上也优于它们，验证了其在几何保真度和参数化设计意图恢复方面的优越性。
英文摘要：
Image-to-CAD generation seeks executable parametric programs that recover both the geometry and design intent of a reference object. Existing systems are commonly evaluated by validity and shape overlap, although two solids with similar volume can encode different CAD relations. We introduce ConCAD, a constraint-aware image-to-CAD framework optimized via Group Relative Policy Optimization (GRPO) with rewards at two complementary granularities: a code-level constraint reward and an execution-level geometric reward. This complementary design disambiguates structurally distinct yet volumetrically similar shapes while ensuring valid 3D geometry. To verify that these rewards recover geometry and design intent, we introduce a B-rep geometric constraint satisfaction rate (G-CSR), which analytically extracts and evaluates geometric constraints from boundary representations. Experiments on the DeepCAD and Zero2CAD demonstrate that ConCAD achieves the best IoU and Chamfer Distance over competitive baselines, while also outperforming them on G-CSR, validating its superior recovery of both geometric fidelity and parametric design intent.
