UniPhysGen：用于可模拟3D资产的统一物理基础
UniPhysGen: Unified Physical Grounding for Simulation-Ready 3D Assets
- Zhejiang University（浙江大学）
- Manycore Tech Inc.（众核科技公司）
- University of Electronic Science and Technology of China（电子科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究针对现有3D资产缺乏统一物理语义问题，提出UniPhys框架及UniPhysGen模型，通过联合推理关节语义和固有物理属性，减轻几何捷径偏差，经实验验证其性能先进，生成资产可用于机器人模拟环境。
AI中文摘要：
物理基础的3D资产在具身人工智能和机器人模拟中日益重要。然而，大多数现有3D资产缺乏现实交互所需的统一物理语义，包括关节语义和固有物理属性。当前方法要么独立处理这些语义，要么依赖规范化对象结构，限制了跨异构3D资产的鲁棒性。我们提出了UniPhys，一个可扩展框架，能自动将原始3D资产转换为具有统一物理语义的可模拟资产。在此基础上构建了大规模数据集UniPhys-40K和统一物理基础评估基准UniPhys-Bench。还引入了统一物理基础模型UniPhysGen，其联合推理关节语义和固有物理属性，减轻了异构部件分解下的几何捷径偏差。大量实验证明其在关节基础和固有物理属性估计任务上的先进性能，生成的资产可直接用于机器人模拟环境进行现实物理交互。
英文摘要：
Physically grounded 3D assets are increasingly important for embodied AI and robotic simulation. However, most existing 3D assets lack unified physical semantics, including articulation semantics and intrinsic physical properties, required for realistic interaction. Current approaches either treat these semantics independently or rely on canonicalized object structures, limiting robustness across heterogeneous 3D assets. We present UniPhys, a scalable framework for automatically transforming raw 3D assets into simulation-ready assets with unified physical semantics. Based on UniPhys, we construct UniPhys-40K, a large-scale physically grounded dataset, together with UniPhys-Bench, a carefully verified benchmark for unified physical grounding evaluation. We further introduce UniPhysGen, a unified physical grounding model that jointly reasons over articulation semantics and intrinsic physical properties. UniPhysGen incorporates geometry-robust articulation grounding to mitigate geometric shortcut bias under heterogeneous part decompositions. Extensive experiments demonstrate state-of-the-art performance across articulation grounding and intrinsic physical property estimation tasks, while the resulting assets can be directly deployed in robotic simulation environments for realistic physical interaction. Our code and dataset will be available at https://github.com/breezexian/UniPhysGen.
