AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
For embodied AI and virtual reality applications, this work provides a more robust and customizable framework for egocentric world simulation, though it is an incremental improvement over existing methods.
AnchorWorld improves egocentric world simulation by using 3D human motion and auxiliary supervision from exogenous viewpoints to handle out-of-view body parts, and introduces anchor views with text descriptions for customizable world evolution. It significantly outperforms state-of-the-art baselines in interaction integrity and customization consistency.
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.