SubDGuide：一种受建模者启发的用于网格到细分曲面（SubD）重建的智能体工作流

中文摘要 AI 辅助

细分曲面通过稀疏控制笼表示自由形式几何，但从密集网格中恢复该控制笼并非单纯的拟合问题：系统必须推断出需要控制的位置、哪些曲线编码设计特征，以及何时应修改初始结果。我们提出SubDGuide，一种受建模者启发的用于此任务的智能体工作流。阶段A读取对齐的多视图几何证据，生成关于控制笼分辨率、特征映射和宽形式拟合的紧凑计划。阶段B检查生成的曲面，请求针对性诊断，并选择修复、回滚或弃权（不执行）操作。几何工具执行并验证每一项更改；规划器从不生成顶点或连接性。在固定评估队列上，SubDGuide在所有五个报告指标上均优于自动重网格化：中值Chamfer-L1从目标边界框对角线的0.641%降至0.443%，1%容差下的F分数从82.00%升至92.78%。与一次性规划相比，有状态反馈在五个报告的中值指标中改善了四个，而当提议无帮助时，验证会保留之前的检查点。同一界面支持六个多模态规划器，展示了语义判断如何指导实用、可检查的网格到SubD工作流。

英文摘要

Subdivision surfaces represent free-form geometry through a sparse control cage, but recovering that cage from a dense mesh is not merely a fitting problem: the system must infer where control is needed, which curves encode design features, and when an initial result should be revised. We present SubDGuide, a modeler-inspired agentic workflow for this task. Stage A reads aligned multiview geometric evidence and produces a compact plan for cage resolution, feature mapping, and broad-form fitting. Stage B inspects the resulting surface, requests targeted diagnostics, and chooses repair, rollback, or stopping actions. Geometry tools execute and verify every change; the planner never generates vertices or connectivity. On a fixed evaluation cohort, SubDGuide improves all five reported metrics over automatic remeshing: median Chamfer-L1 decreases from 0.641% to 0.443% of the target bounding-box diagonal, and F-score at a 1% tolerance increases from 82.00% to 92.78%. Stateful feedback improves four of five reported median metrics over one-shot planning, while verification retains the earlier checkpoint when a proposal is unhelpful. The same interface supports six multimodal planners, showing how semantic judgment can guide a practical, inspectable mesh-to-SubD workflow.

发表机构

• Mercedes-Benz AG（梅赛德斯-奔驰集团）
• Technical University of Darmstadt（达姆施塔特工业大学）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

18 pages, including supplementary material