無限動態：透過程序化生成實現可擴展的高保真關節物體合成

Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation

March 17, 2025

作者: Xinyu Lian, Zichao Yu, Ruiming Liang, Yitong Wang, Li Ray Luo, Kaixu Chen, Yuanzhen Zhou, Qihong Tang, Xudong Xu, Zhaoyang Lyu, Bo Dai, Jiangmiao Pang

cs.AI

摘要

在涉及具身智能的多项任务中，高质量的大规模铰接物体需求迫切。现有的大多数创建铰接物体的方法要么基于数据驱动，要么依赖仿真，这些方法受限于训练数据的规模与质量，或是仿真的精确度与繁重的人工操作。本文提出了一种名为“无限运动”的新颖方法，通过程序化生成来合成高保真度的铰接物体。用户研究和定量评估表明，我们的方法能够生成超越当前最先进技术的结果，在物理属性和网格质量上均与人工标注的数据集相媲美。此外，我们展示了合成数据可用作生成模型的训练数据，为下一步的规模扩展提供了可能。代码已发布于https://github.com/Intern-Nexus/Infinite-Mobility。

English

Large-scale articulated objects with high quality are desperately needed for multiple tasks related to embodied AI. Most existing methods for creating articulated objects are either data-driven or simulation based, which are limited by the scale and quality of the training data or the fidelity and heavy labour of the simulation. In this paper, we propose Infinite Mobility, a novel method for synthesizing high-fidelity articulated objects through procedural generation. User study and quantitative evaluation demonstrate that our method can produce results that excel current state-of-the-art methods and are comparable to human-annotated datasets in both physics property and mesh quality. Furthermore, we show that our synthetic data can be used as training data for generative models, enabling next-step scaling up. Code is available at https://github.com/Intern-Nexus/Infinite-Mobility