cs.CVNov 19, 2026

StreamEgo: Streaming Exocentric-to-Egocentric Video Generation

Authors: Tianyi Xu, Boyang Lyu, Yunkai Tang, Kairan Ding, Jiahang Li, Weiyu Guo, Yandong Guo, Shuchen Weng, 

Organizations: Peking University · AI2 Robotics · Beijing Academy of Artificial Intelligence (BAAI)

Abstract

Exocentric-to-egocentric (Exo2Ego) video generation transforms third-person recordings into first-person viewpoints, unlocking immersive AR/VR experiences and scalable demonstration synthesis for embodied robotics. Extending it to a streaming setting is expected to further enable live applications. However, existing methods suffer from degraded manipulation regions, overfitting and confinement to fixed-length clips with prohibitive latency. To address these limitations, we present StreamEgo, a real-time framework for unbounded, generalizable Exo2Ego video generation. To resolve intricate manipulation dynamics while supporting the streaming pipeline, a streaming dual-branch prior provides pixel-aligned guidance for translating appearance and skeletal kinematics. We also introduce a region-aware loss curriculum to improve generalization and stabilize multi-objective diffusion training. Furthermore, we distill the model into a chunk-wise autoregressive model, augmented with a region-aware corruption mechanism and a first-chunk curriculum, enabling high-quality, generalizable real-time streaming Exo2Ego generation at 24.3 FPS on a single H100 GPU.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Ego-Forge: Text and Geometric-Attention Free Exo-to-Egocentric Video Generation

    Sep 28, 2026Mohammad Mahdi, Luc Van Gool, Danda Pani PaudelCamera-Conditioned Video GenerationVideo Diffusion Models

  2. Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis

    Nov 25, 2025Mohammad Mahdi, Yuqian Fu, Nedko Savov +3Camera-Conditioned Video GenerationVideo Diffusion Models