Reproduce “Ego-Forge: Text and Geometric-Attention Free Exo-to-Egocentric Video Generation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Mohammad Mahdi, Luc Van Gool, Danda Pani Paudel
Ego-Forge generates egocentric video from third-person footage and a target head trajectory, including views unseen by camera. It builds conditioning tokens from changing hidden states and uses a lightweight depth prior, without inference captions or geometry-guided attention. On unseen-scene Ego-Exo4D evaluation, its FVD is 313.95 versus EgoX’s 463.24 and PSNR is 14.60 versus 14.32, but EgoX leads on other metrics.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.