EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses
This addresses the need for fine-grained control in embodied AI agents for simulation and planning, though it appears incremental as it builds on existing video diffusion models with a novel pose representation.
The paper tackles the problem of generating controllable egocentric videos by conditioning on 3D body pose sequences, resulting in a model that produces high-quality, pose-consistent future frames.
Egocentric video generation with fine-grained control through body motion is a key requirement towards embodied AI agents that can simulate, predict, and plan actions. In this work, we propose EgoControl, a pose-controllable video diffusion model trained on egocentric data. We train a video prediction model to condition future frame generation on explicit 3D body pose sequences. To achieve precise motion control, we introduce a novel pose representation that captures both global camera dynamics and articulated body movements, and integrate it through a dedicated control mechanism within the diffusion process. Given a short sequence of observed frames and a sequence of target poses, EgoControl generates temporally coherent and visually realistic future frames that align with the provided pose control. Experimental results demonstrate that EgoControl produces high-quality, pose-consistent egocentric videos, paving the way toward controllable embodied video simulation and understanding.