EgoX

EgoX extends VGGT’s feed-forward reconstruction paradigm from scenes to egocentric hand–object–scene reconstruction. Given egocentric video and a first-frame object mask, it jointly reconstructs hands, object 6DoF poses, depth, and camera motion in shared metric geometry.

Model weights coming soon.

Part of EgoXperience.

Data · Bench · Model

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including ropedia-ai/EgoX