EgoWorld:
Translating Exocentric View to Egocentric View
using Rich Exocentric Observations

arXiv 2025

1AI Lab, LG Electronics, 2KAIST, 3Visual Geometry Group, University of Oxford
(† : Corresponding author)
pipeline

We introduce EgoWorld, a novel two-stage framework that reconstructs egocentric view from rich exocentric observations, including depth maps, 3D hand poses, and textual descriptions.

BibTeX

@article{park2025egoworld,
  author    = {Park, Junho and Ye, Andrew Sangwoo and Kwon, Taein},
  title     = {EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations},
  journal   = {arXiv},
  year      = {2025},
}