EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Videos Generation

Video generation has emerged as a promising tool for world simulation, leveraging visual data to replicate real-world environments. Within this context, egocentric video generation, which centers on the human perspective, holds significant potential for enhancing applications in virtual reality, augmented reality, and gaming. However, the generation of egocentric videos presents substantial challenges due to the dynamic nature of first-person viewpoints, the intricate diversity of actions, and the complex variety of scenes encountered. Existing datasets are inadequate for addressing these challenges effectively. To bridge this gap, we present EgoVid-5M, the first high-quality dataset specifically curated for egocentric video generation. EgoVid-5M encompasses over 5 million egocentric video clips and is enriched with detailed action annotations, including fine-grained kinematic control and high-level textual descriptions. To ensure the integrity and usability of the dataset, we implement a sophisticated data cleansing pipeline designed to maintain frame consistency, action coherence, and motion smoothness under egocentric conditions. Furthermore, we introduce EgoDreamer, which is capable of generating egocentric videos driven simultaneously by action descriptions and kinematic control signals. The EgoVid-5M dataset, associated action annotations, and all data cleansing metadata will be released for the advancement of research in egocentric video generation.

Authors

• Xiaofeng Wang School of Artificial Intelligence, University of Chinese Academy of Sciences Institute of automation, Chinese Academy of Sciences Luoyang Institute for Robot and Intelligent Equipment
• Kang Zhao Tongyi Lab
• Feng Liu
• Jiayu Wang Shanghai Key Lab of Intell. Info. Processing, School of Computer Science, Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing
• Guosheng Zhao School of Artificial Intelligence, University of Chinese Academy of Sciences Institute of automation, Chinese Academy of Sciences Luoyang Institute for Robot and Intelligent Equipment
• Xiaoyi Bao School of Artificial Intelligence, University of Chinese Academy of Sciences Institute of automation, Chinese Academy of Sciences Luoyang Institute for Robot and Intelligent Equipment
• Zheng Zhu GigaAI
• Yingya Zhang Tongyi Lab

Keywords

No keywords are indexed for this paper.