# ZhengPeng7/BiRefNet

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Repository: https://github.com/ZhengPeng7/BiRefNet
Canonical: https://ross.abutalabs.com/products/birefnet
Homepage: https://www.birefnet.cv
Language: Python
License: MIT
License Family: permissive
Topics: dichotomous-image-segmentation, salient-object-detection, camouflaged-object-detection, background-removal, birefnet, image-segmentation, high-resolution-image-segmentation
Last push: 2026-07-24T08:44:29+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 8, longevity 100
- inputs: {"age_days": 1477, "days_push": 40, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4098, forks 321 (observed 2026-08-28T04:08:35.419017+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: image-processing, computer-vision, machine-learning, deep-learning
- domain: computer-vision, image-processing, machine-learning, deep-learning
- platform: python, cross-platform
- tags: image-segmentation, background-removal, salient-object-detection, camouflaged-object-detection, dichotomous-image-segmentation, pytorch, pretrained-models, huggingface, gpu

## Member repositories
- ZhengPeng7/BiRefNet (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:35.419017+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:17.959034+00:00, confidence not recorded.
  - readme: https://github.com/ZhengPeng7/BiRefNet (fetched 2026-08-28T04:08:35.419017+00:00, sha 97cc1a749b0c)
  - homepage: https://www.birefnet.cv (fetched 2026-08-29T09:14:52.831518+00:00, sha df76360e8beb)
- Data as of 2026-08-30T08:39:29.467469+00:00.