DepthAnything/Depth-Anything-V2 — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #5693 · UNIT ID 814827405

DepthAnything/Depth-Anything-V2

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00186

ENGAGEMENT0.30

FRESHNESS1.00

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

0% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

5.33

ACCEL

-0.50

RETENTION

64.3%

PEAK 2026-08-26 · FORK-RETENTION 0.0% · 16 STARS / WINDOW

Author Audience

AUDIENCE

2,825

FOLLOWERS

216

OWNER ★

11,965

Engagement Signals

FORKS

901

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 16 / 16 (DIVERSITY 1.00)

Why This Is A Finding

DepthAnything/Depth-Anything-V2 собрал 16 звёзд за окно, тогда как у автора всего 216 подписчиков — эффективная аудитория ≈ 2,825. Это даёт surprise-индекс 0.00186 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 40% OF 9558 FINDINGS

#03wang2122/sprix-sage-router[ PYTHON ]0.80 #04zeenie-ai/OpenCompany[ PYTHON ]0.78 #20HRuiCcc/music-geshizhuanhuan[ PYTHON ]0.41 #22MerZlin/dsh-pet-indesktop[ PYTHON ]0.39 #24handsomejustin/easy_tdx[ PYTHON ]0.38

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9558 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 40%

VELOCITY5.335.67-0.33ABOVE 46%

RETENTION64.3%42.9%+21.4 PPABOVE 72%

FORKS901333+568ABOVE 69%

SURPRISE0.000.00-0.00ABOVE 36%