EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses

TL;DR

EgoControl is a novel diffusion-based model that generates realistic egocentric videos conditioned on explicit 3D body poses, enabling precise control over motion and camera dynamics for embodied AI applications.

Contribution

It introduces a new pose representation and control mechanism within a video diffusion model for fine-grained, pose-controllable egocentric video generation.

Findings

Produces high-quality, pose-consistent videos

Achieves temporally coherent and realistic frame synthesis

Demonstrates effective control over camera and body movements

Abstract

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.