PhysX-Anything：从单张图像生成仿真就绪的物理三维资产
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image
提出一种基于 VLM 的物理 3D 生成框架，通过高效几何词元化（减少 193 倍词元）在标准 VLM 词元预算内学习显式几何，并联合预测铰接与物理属性，为单图生成可直接用于仿真的铰接资产提供了新思路。
原文依据 the first VLM-based physical 3D generative model, along with a new 3D representation that efficiently tokenizes geometry
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维建模正从静态视觉表示转向可直接用于仿真与交互的物理铰接资产。然而，现有大多数三维生成方法忽略了关键的物理与铰接属性，从而限制了它们在具身智能中的实用性。为弥补这一差距，我们提出 PhysX-Anything，这是首个仿真就绪的物理三维生成框架，给定单张野外图像即可生成具有显式几何、铰接和物理属性的高质量仿真就绪三维资产。具体而言，我们提出了首个基于视觉语言模型（VLM）的物理三维生成模型，以及一种能高效词元化几何的新三维表示。它将词元数量减少 193 倍，使得在标准 VLM 词元预算内进行显式几何学习成为可能，且在微调过程中无需引入任何特殊词元，并显著提升了生成质量。此外，为克服现有物理三维数据集多样性有限的不足，我们构建了一个新数据集 PhysX-Mobility，它将先前物理三维数据集中的物体类别扩展了 2 倍以上，包含超过 2K 个具有丰富物理标注的常见真实世界物体。在 PhysX-Mobility 和野外图像上的大量实验表明，PhysX-Anything 具有强大的生成性能和稳健的泛化能力。此外，在 MuJoCo 风格环境中的仿真实验验证了我们的仿真就绪资产可直接用于接触丰富的机器人策略学习。我们相信 PhysX-Anything 能大幅赋能广泛的下游应用，尤其是在具身智能和基于物理的仿真领域。
英文原文摘要 1678 字符
3D modeling is shifting from static visual representations toward physical, articulated assets that can be directly used in simulation and interaction. However, most existing 3D generation methods overlook key physical and articulation properties, thereby limiting their utility in embodied AI. To bridge this gap, we introduce PhysX-Anything, the first simulation-ready physical 3D generative framework that, given a single in-the-wild image, produces high-quality sim-ready 3D assets with explicit geometry, articulation, and physical attributes. Specifically, we propose the first VLM-based physical 3D generative model, along with a new 3D representation that efficiently tokenizes geometry. It reduces the number of tokens by 193x, enabling explicit geometry learning within standard VLM token budgets without introducing any special tokens during fine-tuning and significantly improving generative quality. In addition, to overcome the limited diversity of existing physical 3D datasets, we construct a new dataset, PhysX-Mobility, which expands the object categories in prior physical 3D datasets by over 2xand includes more than 2K common real-world objects with rich physical annotations. Extensive experiments on PhysX-Mobility and in-the-wild images demonstrate that PhysX-Anything delivers strong generative performance and robust generalization. Furthermore, simulation-based experiments in a MuJoCo-style environment validate that our sim-ready assets can be directly used for contact-rich robotic policy learning. We believe PhysX-Anything can substantially empower a broad range of downstream applications, especially in embodied AI and physics-based simulation.