New
AI & RoboticsMore in AI & Robotics →
Naver’s Seoul World Model Tries to Fix a Core Weakness in Generative Video
By grounding video generation in 1.2 million real street-view images, Naver says its Seoul World Model can produce more consistent city-scale scenes than fully synthetic world models.
Key Takeaways
- SWM uses 1.2 million Naver Map panoramic images.
- The model generates video from coordinates, camera movement, and text prompts.
DE
DT Editorial AI··via the-decoder.com