AI 造 3D 零件不再是一团软泥，而是能改的代码
现在的 AI 从一张图生成 3D 模型，看着唬人，但细节是糊的：该有的棱角是圆的，没有零件之分，你想改个尺寸无从下手。这篇换了个思路：不让 AI 直接画形状，而是让它写代码——把物体拆成一个个有名有姓的零件，用机器能检查的方式拼起来，每个零件的位置不是猜的，而是按连接关系算出来。它还能给每个零件标材质、验证关节能不能动。结果在硬表面物体(机械零件这类)上，它生成的模型棱角最锋利，质量超过所有之前的 AI 生成器，而且输出是带结构的程序，你真能上手改。对普通人来说，这不是明天就能用的工具，而是 3D 建模行业的一个信号：AI 建模正在从“画得像”转向“做得对、可修改”。
📄 原文摘要(英文)
Native 3D generators now recover impressive mesh geometry from a single image. However, a dense mesh stays soft where a machined object should be sharp, it carries no part decomposition, and it exposes no parameter a user could edit. To address this, we explore the paradigm of 3D shape as code, leveraging and scaling the coding ability of an LLM for 3D modeling. We introduce Procedura, a novel 3D modeling agent framework that writes an object as a procedural assembly, a parametric program whose named parts are joined by typed, machine-checkable mates. From a text prompt, the agent plans the object as an assembly graph and writes the program part by part, solving each placement from the mated frames rather than guessing it, and admitting a part only once compile, mate, and connectivity checks pass. A decoupled vision critic then refines the assembly one diagnosed fix at a time. Moreover, the same graph carries per-part materials and a simulator-validated articulation. We evaluate on P3D-Bench under its assembly judge, and with the same judge on MechBench-36, our hard-surface benchmark. On both, Procedura outperforms state-of-the-art native 3D generators and every prior 3D-code agent on judged quality, produces the sharpest edges of any method we evaluate, and is the only one whose output is an editable, part-structured program.