EgoForce: Robust Online Egocentric Motion Reconstruction via Diffusion Forcing

Seoul National University

1. Online Reconstruction Pipeline


EgoForce formulates egocentric reconstruction as a causal generation problem with temporally evolving uncertainty. The denoising network performs a fixed $\Delta k$ refinement step to fully denoise the current pose while progressively refining future predictions. This refinement is conditioned only on the generated history and current observations under a strict causal setting , thereby successfully adapt the expressive power of diffusion models to an online streaming environment.