Python
BardOfCodes/superfit
Fit compact primitive assemblies (SuperFrusta, cuboids, superquadrics) to 3D shapes via residual fitting. CVPR 2026.
★ 126
Stars
10 forks · 0 open issues
+1.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
14.8
Momentum / 100
see the breakdown below
11mo ago
Created
last push 5mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 1.1 | +1.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 6.4 | last week ran 1.43× the monthly pace |
| Freshness | 15 | 1.1 | last push 5mo ago; decays to zero at 180 days |
| Scale | 15 | 6.1 | 126 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 14.8 | sum of the above |
Detail
| Topics | 3d3d-reconstructioncomputer-visioncudacvpr2026primitive-fittingpytorchshape-abstractionshape-decompositionsuperquadrics |
| Matched on | Computer Vision (computer-vision) |
| Short window | +1 stars over 7 days = 0.1/day |
| Long window | +2 stars over 20 days = 0.1/day |
| Lifetime average | 0.38 stars/day over 331 days |
| First seen here | 2026-10-16 |
| Last read | 2d ago |