AnchorWorld: 具身自我中心世界模拟与基于视角的演化定制

摘要

尽管交互式世界建模是一个关键的前沿领域，但在实际场景所需的多样化可控性方面仍探索不足。为弥补这一差距，我们提出AnchorWorld框架，通过增强交互完整性和灵活的世界定制机制推动自我中心模拟的发展。首先，我们以3D人体运动作为主要交互模态。为补充自我中心视角中视野外或被截断的身体部位，我们引入了一种辅助训练监督方法，该方法整合了与智能体第一人称感知系统解耦的外源视角。这使得模型能够观察智能体相对于环境的全身位置，从而促进人-世界交互更稳健的空间 grounding。此外，我们提出了一种简单而有效的机制来实现自演化世界的定制。该机制通过在统一的世界坐标系中定义锚点视图，并结合描述局部场景动态演化的文本描述来实现。实验结果表明，AnchorWorld显著优于最先进的基线模型，消融研究验证了我们关键设计的有效性。值得注意的是，我们的定制方案展现出令人满意的时空几何一致性，并严格遵循预设的演化动力学。

English

Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we present AnchorWorld, a framework that advances egocentric simulation through enhanced interaction integrity and a flexible mechanism for world customization. First, we utilize 3D human motion as the primary interaction modality. To complement the out-of-view or truncated body parts in egocentric views, we introduce an auxiliary training supervision that incorporates exogenous viewpoints decoupled from the agent's first-person sensorium. It allows the model to observe the agent's full-body positioning relative to the environment, facilitating a more robust spatial grounding of human-world interactions. Furthermore, we propose a simple yet effective mechanism for customizing self-evolving worlds. This is achieved by defining anchor views within a unified world coordinate system, coupled with textual descriptions dictating the dynamic evolution of local scenes. Experimental results show that AnchorWorld significantly outperforms state-of-the-art baselines, while ablation studies validate the effectiveness of our key designs. Notably, our customization scheme exhibits promising spatio-temporal geometric consistency and adheres strictly to the prescribed evolutionary dynamics.