Python · Apache-2.0
fundamentalvision/BEVFormer
[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
★ 4.6k
Stars
756 forks · 183 open issues
+1.1/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
19.8
Momentum / 100
see the breakdown below
4y ago
Created
last push 2y ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 6.3 | +1.1/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 2.8 | last week ran 1.19× the monthly pace |
| Freshness | 15 | 0.0 | last push 2y ago; decays to zero at 180 days |
| Scale | 15 | 10.6 | 4.6k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 19.8 | sum of the above |
Detail
| Topics | autonomous-drivingcomputer-visiondeep-learningobject-detection |
| Matched on | Computer Vision (object-detection) |
| Short window | +8 stars over 7 days = 1.1/day |
| Long window | +25 stars over 26 days = 1.0/day |
| Lifetime average | 2.76 stars/day over 1,681 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |