ZhengPeng7/BiRefNet

Health v2 · maintenance only

Adoption not part of the score

4247 stars · 336 forks observed · 2026-10-04

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

BiRefNet is a PyTorch implementation of the CAAI AIR 2024 paper 'Bilateral Reference for High-Resolution Dichotomous Image Segmentation'. It provides pretrained models for high-resolution binary segmentation tasks such as salient object detection, camouflaged object detection, and background removal.

Use cases

• remove background from images
• segment salient objects in high-resolution photos
• detect camouflaged objects in images
• extract subject masks for e-commerce product photos
• segment medical or industrial images
• run image matting for AR and video production

When to choose

• you need state-of-the-art high-resolution binary segmentation masks
• you want pretrained models for background removal or DIS
• you need salient or camouflaged object detection with fine details

When to avoid

• you need multi-class semantic segmentation rather than binary masks
• you have no GPU and need real-time inference on edge devices
• you want a plug-and-play GUI app rather than a model/codebase

Facets

library · maturity active

image-processing computer-vision machine-learning deep-learning computer-vision image-processing machine-learning deep-learning python cross-platform image-segmentation background-removal salient-object-detection camouflaged-object-detection dichotomous-image-segmentation pytorch pretrained-models huggingface gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ZhengPeng7/BiRefNet")