xuebinqin/U-2-Net

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

9853 stars · 1619 forks observed · 2026-08-28

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

Official PyTorch implementation of U^2-Net, a nested U-structure deep network for salient object detection, published in Pattern Recognition 2020. It provides pretrained models commonly used for image background removal, portrait drawing, and object segmentation.

Use cases

• remove background from images
• salient object detection in photos
• segment the main subject of an image
• generate portrait sketches from photos
• run object segmentation on mobile apps
• preprocess images for e-commerce product photos

When to choose

• you need lightweight, accurate salient object detection with pretrained weights
• you want background removal to power a larger pipeline or app
• you want a well-cited research model with an Apache-2.0 license

When to avoid

• you need general-purpose semantic segmentation of many object classes
• you need actively developed features or frequent updates
• you need real-time video segmentation on CPU-only hardware

Facets

library · maturity maintenance

image-processing computer-vision deep-learning machine-learning computer-vision image-processing deep-learning machine-learning python cross-platform salient-object-detection image-segmentation background-removal u2net pytorch portrait-generation gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="xuebinqin/U-2-Net")