RFW-A: Agentic Procedural Generation of 400K Articulated Assets over 500 Categories

📄 arXiv: 2610.40333v1 📥 PDF

作者: Yuanbo Lyu, Changjian Pan, Saining Zhang, Yi Yang, Peishuo Li, Zhiheng Li, Jialu Liu, Junhao Chen, Jiawei Weng, Yupeng Gao, Weiqing Xiao, Wenyi Li, Jiarui Guo, Rui Zhang, Jingrun Du, Weiyi Lin, Zenan Meng, Hu Wei, Lin Qu, Zongzheng Zhang, Hao Zhao, Chaojian Li

分类: cs.CV

发布日期: 2026-10-29

备注: 37 pages, 19 figures. Project Page: https://brain-labbb.github.io/RFW_A_web/


💡 一句话要点

提出RFW-A以高效生成40万类人形资产解决构建难题

🎯 匹配领域: 支柱一:机器人控制 (Robot Control)

关键词: 人形资产生成 程序合成 智能系统 物理模拟 高效建模 机器学习 计算机视觉

📋 核心要点

  1. 现有方法在大规模构建高质量人形资产时面临高人力成本和重复推理的挑战。
  2. RFW-A通过结合智能合成与程序生成,组织可重用组件,优化资产构建流程。
  3. 实验结果显示,RFW-A-400K生成的资产在结构和运动有效性上表现良好,且训练效果显著提升。

📝 摘要(中文)

高质量的人形资产对于具身感知、模拟和操作至关重要,但大规模构建仍然困难。手动标注和程序建模需要大量人力。尽管最近的智能系统通过程序合成自动化资产构建,但每个新资产都需重复昂贵的推理和优化。本文提出RFW-A,结合智能合成与程序生成,组织可重用组件和依赖关系,构建类别级生成器,最终实现高效的资产生成。RFW-A-400K包含超过40万个可用于模拟的人形资产,实验表明其在结构和运动有效性上表现优异,并且在物理模拟器中执行稳定。

🔬 方法详解

问题定义:本文旨在解决高质量人形资产大规模构建的难题,现有方法需大量人力进行手动标注和程序建模,且每个新资产的构建都需重复推理和优化,效率低下。

核心思路:RFW-A的核心思路是利用类别内资产共享构建逻辑,通过智能合成生成可重用的程序,并结合程序执行来高效生成多样化资产。

技术框架:RFW-A的整体架构包括现有的可动程序、可重用组件的组织、类别级生成器的构建,以及通过采样配置和运动状态进行测试和优化的过程。

关键创新:RFW-A的主要创新在于将智能合成与程序生成相结合,允许生成器在不需要额外模型调用的情况下,通过程序执行生成多样化资产,这与传统方法的逐个资产构建方式有本质区别。

关键设计:在设计中,生成器的创建成本平均为$10.62,经过200个资产的摊销后,每个资产的成本降至$0.05,显著低于传统的每个资产$1.24的合成成本。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明,RFW-A-400K生成的资产在结构和运动有效性上具有高稳定性,且在物理模拟器中表现良好。此外,使用RFW-A进行训练的模型在已见和未见类别的部件级关节估计上均有显著提升,验证了其在实际应用中的有效性。

🎯 应用场景

该研究的潜在应用领域包括游戏开发、虚拟现实、动画制作等,能够显著降低高质量人形资产的构建成本和时间,提高生产效率。未来,RFW-A的技术可扩展至其他类型资产的生成,推动相关领域的发展。

📄 摘要(原文)

High-quality articulated assets are essential for embodied perception, simulation, and manipulation, yet constructing them at scale remains difficult. Manual annotation and procedural modeling require substantial human effort. Recent agentic systems automate asset construction through program synthesis, but repeat costly reasoning and refinement for every new asset. Our key observation is that assets within a category can share construction logic despite variations in structure and appearance. Agentic synthesis and procedural generation are therefore complementary: agents can construct reusable programs, while procedural execution reuses the resulting logic across many samples. We therefore present RFW-A, which combines the two in a new articulated-asset generation paradigm. Starting from existing articulated programs, RFW-A organizes reusable components and their dependencies into category-level generators. Agents test and refine these generators across sampled configurations and motion states. Once constructed and validated, the generators produce diverse assets through procedural execution with no further model calls or token charges. The estimated API cost of generator authoring averages $10.62, amortizing to $0.05 per asset over 200 assets, versus $1.24 for the sampled per-asset agentic synthesis baseline. Using RFW-A, we built RFW-A-400K, containing over 400K sim-ready articulated assets across more than 500 categories. Experiments show high structural and kinematic validity and stable execution across physics simulators. Beyond asset validity, training with RFW-A-400K improves part-level articulation estimation on seen and unseen categories, while policies trained in simulation with retrieved and program-edited assets transfer zero-shot to real articulated objects.