Reproduce “StreamEgo: Streaming Exocentric-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

Tianyi Xu, Boyang Lyu, Yunkai Tang, Kairan Ding, Jiahang Li, Weiyu Guo, Yandong Guo, Shuchen Weng and 1 more

StreamEgo converts third-person video into a streaming first-person view. It incrementally builds pixel-aligned visual and skeletal guidance, then generates causal chunks using past outputs as memory. On Ego-Exo4D UNSEEN, its student reaches 37.49% [email protected] and 41.13% Motion-Consistency, versus EgoX’s 11.07% and 15.41%. The task still requires calibrated cameras and a target egocentric trajectory.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.