xuebinqin/DIS resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2568 stars · 289 forks observed · 2026-08-28

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

Official repository for the ECCV 2022 paper 'Highly Accurate Dichotomous Image Segmentation' (DIS), providing the DIS dataset, IS-Net model code, and pretrained weights like isnet-general-use.pth. It focuses on highly accurate segmentation of highly detailed objects, commonly used for background removal.

Use cases

• remove background from images with deep learning
• segment highly detailed objects accurately
• download pretrained IS-Net model weights
• run inference on custom images with isnet-general-use
• train dichotomous image segmentation models
• try a hosted demo for background removal

When to choose

• you need state-of-the-art high-resolution object segmentation or background removal
• you want the official DIS dataset and IS-Net reference implementation
• you are doing research on dichotomous image segmentation

When to avoid

• you need the unreleased DIS V2.0 dataset and model
• you want a production-ready background removal service rather than research code
• you need segmentation of categories underrepresented in DIS V1.0 like animals or humans

Facets

dataset · maturity maintenance

image-processing computer-vision deep-learning machine-learning computer-vision image-processing deep-learning machine-learning python cross-platform image-segmentation background-removal dichotomous-image-segmentation u2net isnet eccv-2022 salient-object-detection model-weights

Member repositories

For agents

markdown · JSON · MCP: product_card(name="xuebinqin/DIS")