graphdeco-inria/gaussian-splatting — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #3124 · UNIT ID 662028682

graphdeco-inria/gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0115

ENGAGEMENT0.35

FRESHNESS1.01

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

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

2% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

81.14

ACCEL

+30.07

RETENTION

50.4%

PEAK 2026-08-26 · FORK-RETENTION 64.8% · 568 STARS / WINDOW

Author Audience

AUDIENCE

6,991

FOLLOWERS

643

OWNER ★

28,527

Engagement Signals

FORKS

3,399

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 568 / 568 (DIVERSITY 1.00)

Why This Is A Finding

graphdeco-inria/gaussian-splatting собрал 568 звёзд за окно, тогда как у автора всего 643 подписчиков — эффективная аудитория ≈ 6,991. Это даёт surprise-индекс 0.0115 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 64.8% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 68% OF 9760 FINDINGS

#08MddIdd/mdd-sim-gateway[ PYTHON ]0.41 #17litaolemo/xtquant_big_convert[ PYTHON ]0.36 #20LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler[ PYTHON ]0.34 #24zeenie-ai/OpenCompany[ PYTHON ]0.30 #25917Dhj/DeepPaperNote[ PYTHON ]0.29

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9760 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.00ABOVE 68%

VELOCITY81.143.71+77.43ABOVE 97%

RETENTION50.4%38.0%+12.4 PPABOVE 70%

FORKS3,39986+3,313ABOVE 98%

SURPRISE0.010.01+0.00ABOVE 54%