EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents

ArXi:2602.23205v2 Announce Type: replace Human behaviors in the real world naturally encode rich, long-term contextual information that can be leveraged to train embodied agents for perception, understanding, and acting. However, existing capture systems typically rely on costly studio setups and wearable devices, limiting the large-scale collection of scene-conditioned human motion data in the wild. To address this, we propose EmbodMocap, a portable and affordable data collection pipeline using two moving iPhones.