URDF-Anything+:面向仿真就绪铰接资产的端到端生成
URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets
AI总结:
提出URDF-Anything+,一种端到端自回归扩散框架,从单张RGB图像直接生成仿真就绪的URDF模型,统一建模部件几何与铰接结构。
摘要:
铰接物体是机器人学、物理仿真和交互式虚拟环境的基础。然而,从视觉观测中恢复它们本质上具有挑战性,因为图像仅提供关于部件几何及其底层运动学结构的部分和模糊线索。现有方法通常依赖多阶段流水线、从资产库检索或显式部件分割。我们提出URDF-Anything+,一种端到端自回归扩散框架,直接从单张RGB图像生成仿真就绪的URDF模型。以视觉观测和物体几何为条件,URDF-Anything+在结构化潜在空间中运行,并在统一生成过程中联合建模部件几何和铰接。具体而言,模型顺序预测每个铰接部件及其关联的关节参数,同时一个终止标记动态确定部件数量。这种设计使得无需外部检索或后处理阶段即可直接生成完全可执行的URDF。在大规模铰接物体基准上的实验表明,URDF-Anything+在几何重建质量、关节参数估计和物理可执行性方面优于先前方法,同时比现有多阶段方法显著更高效。此外,生成的URDF作为忠实数字孪生,使得纯仿真训练的操作策略能够零样本迁移。
英文摘要:
Articulated objects are fundamental for robotics, simulation of physics, and interactive virtual environments. However, recovering them from visual observations is inherently challenging, as images provide only partial and ambiguous cues about both part geometry and their underlying kinematic structure. Existing approaches typically rely on multi-stage pipelines, retrieval from asset libraries, or explicit part segmentation. We present URDF-Anything+, an end-to-end autoregressive diffusion framework that generates simulation-ready URDF models directly from a single RGB image. Conditioned on visual observations and object geometry, URDF-Anything+ operates in a structured latent space and jointly models part geometry and articulation in a unified generation process. Specifically, the model sequentially predicts each articulated part together with its associated joint parameters, while a termination token dynamically determines the number of parts. This design enables direct generation of fully executable URDFs without external retrieval or post-processing stages. Experiments on large-scale articulated object benchmarks demonstrate that URDF-Anything+ outperforms prior methods in geometric reconstruction quality, joint parameter estimation, and physical executability, while being substantially more efficient than existing multi-stage approaches. Furthermore, the generated URDFs serve as faithful digital twins, enabling the zero-shot transfer of manipulation policies trained purely in simulation.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。