A Survey of Interactive Generative Video
Jiwen Yu, Yiran Qin, Haoxuan Che, Quande Liu, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai, Hao Chen, Xihui Liu
2025-05-02
Summary
This paper talks about Interactive Generative Video, which is a new kind of AI technology that not only creates videos but also lets people interact with them in real time, opening up lots of new possibilities for things like video games and self-driving cars.
What's the problem?
Making videos that you can control and interact with as they're being created is really hard for AI, because it has to handle things like quick reactions, remembering what has happened, and making sure everything looks and moves realistically.
What's the solution?
The researchers reviewed the latest methods and challenges in this area, exploring how different AI systems are being designed to generate videos that can respond to user input, keep track of changes, and act intelligently in different situations.
Why it matters?
This matters because it could lead to more realistic and engaging video games, smarter robots, and better training tools for things like driving, making technology more interactive and useful in everyday life.
Abstract
Interactive Generative Video (IGV) combines generative capabilities with interactive features to enable diverse applications across gaming, embodied AI, and autonomous driving, focusing on challenges such as real-time generation, control, memory, dynamics, and intelligence.