PhysGen：面向工业设计的物理落地三维形状生成
PhysGen: Physically Grounded 3D Shape Generation for Industrial Design
把物理属性（如气动效率）作为显式引导信号注入流匹配采样过程，通过速度更新与物理精修的交替迭代在潜空间中调整形状；做 3D 生成且关心下游功能约束的工作可复用这一「生成器+物理正则+联合潜空间编码」的范式。
原文依据 we introduce a new flow matching model with explicit physical guidance, consisting of an alternating update process
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的三维形状生成模型能够合成高保真且视觉上合理的形状。对于经过工程设计流程的某些类别形状而言，形状的真实感与其底层物理属性紧密耦合，例如汽车的气动效率。由于现有方法缺乏此类物理知识，它们无法利用这些知识来提升形状生成的真实感。受此启发，我们提出了一套统一的、基于物理的三维形状生成流程，重点关注工业设计应用。具体而言，我们引入了一个带有显式物理引导的新型流匹配模型，它由交替更新过程构成。我们迭代地执行基于速度的更新与基于物理的精修，逐步调整潜变量，使其与期望的三维形状和物理属性对齐。我们进一步将物理感知正则项引入基于速度的更新步骤，以增强物理有效性。为支持此类物理引导的更新，我们构建了一个形状与物理变分自编码器（SP-VAE），它将形状与物理信息联合编码到统一的潜空间中。在三个基准上的实验表明，这种协同式建模提升了形状的真实感，使其超越单纯的视觉合理性。我们的代码与模型权重已发布于 https://github.com/kasvii/PhysGen。
英文原文摘要 1414 字符
Existing generative models for 3D shapes can synthesize high-fidelity and visually plausible shapes. For certain classes of shapes that have undergone an engineering design process, the realism of the shape is tightly coupled with the underlying physical properties, e.g., aerodynamic efficiency for automobiles. Since existing methods lack knowledge of such physics, they are unable to use this knowledge to enhance the realism of shape generation. Motivated by this, we propose a unified physics-based 3D shape generation pipeline, with a focus on industrial design applications. Specifically, we introduce a new flow matching model with explicit physical guidance, consisting of an alternating update process. We iteratively perform a velocity-based update and a physics-based refinement, progressively adjusting the latent code to align with the desired 3D shapes and physical properties. We further strengthen physical validity by incorporating a physics-aware regularization term into the velocity-based update step. To support such physics-guided updates, we build a shape-and-physics variational autoencoder (SP-VAE) that jointly encodes shape and physics information into a unified latent space. The experiments on three benchmarks show that this synergistic formulation improves shape realism beyond mere visual plausibility. Our code and model weights are available at https://github.com/kasvii/PhysGen.