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

TL;DR

EmbodMocap introduces a portable, dual-iPhone system for in-the-wild 4D human-scene reconstruction, enabling large-scale, scene-consistent data collection without static setups.

Contribution

A novel, affordable dual-iPhone pipeline for metric-scale, scene-aware human motion capture in everyday environments, improving over monocular methods.

Findings

Achieves superior alignment and reconstruction compared to single iPhone or monocular models.

Enables training of models for human-scene reconstruction, physics-based animation, and robot motion control.

Validated through experiments demonstrating pipeline effectiveness and applications in embodied AI.

Abstract

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. Our key idea is to jointly calibrate dual RGB-D sequences to reconstruct both humans and scenes within a unified metric world coordinate frame. The proposed method allows metric-scale and scene-consistent capture in everyday environments without static cameras or markers, bridging human motion and scene geometry seamlessly. Compared with optical capture ground truth, we demonstrate that the dual-view setting exhibits a remarkable ability to mitigate depth ambiguity, achieving superior alignment and reconstruction performance over single iphone or monocular models. Based on the collected data, we empower three embodied AI tasks: monocular human-scene-reconstruction, where we fine-tune on feedforward models that output metric-scale, world-space aligned humans and scenes; physics-based character animation, where we prove our data could be used to scale human-object interaction skills and scene-aware motion tracking; and robot motion control, where we train a humanoid robot via sim-to-real RL to replicate human motions depicted in videos. Experimental results validate the effectiveness of our pipeline and its contributions towards advancing embodied AI research.