BirdDreams model released
The story so far
qwen has launched BirdDreams, a self-regressive driving world model that integrates perspective and BEV video generation. The model generates perspective videos and bird's-eye view videos (BEV), making scene layout a part of predicting the future, reducing occlusion and preserving scene details. On the PhysicalAI-AV and nuScenes datasets, BirdDreams more faithfully follows the input trajectory and generates more reasonable self-motion than previous models, without requiring HD maps or vehicle state input.
AI-written from the reports · Updated yesterday
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersBirdDreams: Joint Perspective and BEV Video Generation for Reasonable, Reactive Driving World Models
BirdDreams jointly generates bird's-eye view (BEV) videos and bird's-eye view videos, making scene layout a part of predicting the future. By providing an overhead view of vehicle position and movement through BEV, it reduces occlusion, while the perspective video retains scene details. On PhysicalAI-AV and nuScenes, BirdDreams more faithfully follows the input trajectory of its own vehicle and generates more reasonable self-motion without HD map or vehicle state input.
Heat over time
- Now
- 3
- Peak
- 813 Nov, 14:00
- 24h change
- -49%
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.