ZFTurbo/Weighted-Boxes-Fusion

Health v2 · maintenance only

Adoption not part of the score

1827 stars · 235 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python library implementing several methods for ensembling bounding boxes from multiple object detection models, including Non-maximum Suppression, Soft-NMS, Non-maximum Weighted, and Weighted Boxes Fusion (WBF). It supports 2D and 3D boxes and model weighting.

Use cases

• ensemble predictions from multiple object detection models
• replace NMS with weighted boxes fusion for better accuracy
• merge bounding boxes from several models into one output
• apply soft-NMS to detection results
• fuse 3D bounding boxes from detection models
• improve mAP in detection competitions by combining model outputs

When to choose

• you have predictions from multiple object detection models and want to combine them
• you want better ensembling results than plain NMS
• you need a lightweight pip-installable utility for box fusion in Python

When to avoid

• you need full object detection model training or inference
• you work outside Python or need GPU-accelerated fusion at scale
• your task is not bounding-box based detection

Facets

library · maturity stable

machine-learning computer-vision image-processing computer-vision machine-learning deep-learning python cross-platform object-detection ensemble weighted-boxes-fusion nms bounding-boxes

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ZFTurbo/Weighted-Boxes-Fusion")