arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.13947cs.CV

面向物理可落地的铰接式3D资产：多智能体流水线与基准测试

Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark

Nanyang Technological University（南洋理工大学）；ETH Zurich（苏黎世联邦理工学院）；Microsoft（微软公司）；University of Cambridge（剑桥大学）；University of Oxford（牛津大学）

Xudong Cai, Ruijie Zhu, Haoliang Shang, Ruining Li, Marc Pollefeys, Shangzhe Wu, Andrea Vedaldi, Chuanxia Zheng

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出带物理模拟反馈的多智能体流水线系统Artisan，构建含多维度指标的统一基准，在10余种模型评估中实现低碰撞率、高稳定性，为3D生成发展提供见解。

摘要：

本文研究物理可落地的铰接式3D资产生成，将目标从复现物体外观转向捕捉其运动与功能。受程序化生成和智能体生成相关文献启发，我们提出Artisan系统，该系统扩展了最新方法Articraft，引入带物理模拟反馈的多智能体流水线，可实现几何、外观之外的综合属性，以及物理上合理的铰接效果，如无碰撞运动、重力下的稳定性、准确的质量与材质属性。此外，我们构建了涵盖空间保真度、物理合理性、下游任务性能、整体质量四个关键方面的统一基准，该基准包含来自ArtVIP和LightWheel的100个参考资产、50个稳定性提示，以及50个带有参考质量的ABO对象，具备评估各类指标的协议。通过对10余种代表性模型的广泛评估，Artisan在实现有竞争力的空间保真度的同时，在评估方法中达到最低碰撞率和最高稳定性率。我们的系统与基准为推进3D生成向物理合理、功能可用的资产发展提供了见解。

英文摘要：

In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objects look to capturing how they move and function. Inspired by the literature on procedural and agentic generation, we present Artisan, a system that extends the latest method Articraft by introducing a multi-agent pipeline with physical simulation feedback, enabling comprehensive attributes beyond geometry, appearance, and physically plausible articulation, such as collision-free motion, stability under gravity, and accurate mass and material properties. Furthermore, we construct a unified benchmark spanning four key aspects: spatial fidelity, physical plausibility, downstream task performance, and overall quality. The benchmark encompasses 100 reference assets from ArtVIP and LightWheel, 50 stability prompts, and 50 ABO objects with reference masses, with protocols evaluating various metrics. Through extensive evaluation of more than 10 representative models, Artisan achieves competitive spatial fidelity while attaining the lowest collision rates and highest stability rates among the evaluated methods. Together, our system and benchmark establish insights for advancing 3D generation towards physically plausible, functionally usable assets.

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。

↑