SceneScape: Text-Driven Consistent Scene Generation
–Neural Information Processing Systems
We present a method for text-driven perpetual view generation - synthesizing long-term videos of various scenes solely from an input text prompt describing the scene and camera poses.
Neural Information Processing Systems
Oct-8-2025, 23:26:05 GMT
- Country:
- Asia
- Japan > Honshū
- Chūbu
- Ishikawa Prefecture > Kanazawa (0.04)
- Nagano Prefecture > Nagano (0.04)
- Chūbu
- Middle East > Israel (0.04)
- Japan > Honshū
- Asia
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (0.94)
- Natural Language (1.00)
- Vision (1.00)
- Information Technology > Artificial Intelligence