Python · MIT
Vooban/Smoothly-Blend-Image-Patches
Using a U-Net for image segmentation, blending predicted patches smoothly is a must to please the human eye.
★ 382
Stars
90 forks · 13 open issues
flat
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
7.5
Momentum / 100
see the breakdown below
9y ago
Created
last push 6y ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | flat, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 0.0 | last push 6y ago; decays to zero at 180 days |
| Scale | 15 | 7.5 | 382 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 7.5 | sum of the above |
Detail
| Topics | cnnimage-segmentationsemantic-segmentationu-net |
| Matched on | Computer Vision (image-segmentation) |
| Short window | +0 stars over 7 days = 0.0/day |
| Long window | +0 stars over 26 days = 0.0/day |
| Lifetime average | 0.11 stars/day over 3,359 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |