metadata

library_name: BiRefNet
tags:
  - background-removal
  - mask-generation
  - Image Matting
  - pytorch_model_hub_mixin
  - model_hub_mixin
repo_url: https://github.com/ZhengPeng7/BiRefNet-portrait
pipeline_tag: image-segmentation

Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Peng Zheng^1,4,5,6, Dehong Gao², Deng-Ping Fan^1*, Li Liu³, Jorma Laaksonen⁴, Wanli Ouyang⁵, Nicu Sebe⁶

¹Nankai University ²Northwestern Polytechnical University ³National University of Defense Technology ⁴Aalto University ⁵Shanghai AI Laboratory ⁶University of Trento

This repo holds the official weights of BiRefNet for general matting.

Training Sets:

P3M-10k (except TE-P3M-500-P)
TR-humans

Validation Sets:

TE-P3M-500-P

Performance:

Dataset	Method	Smeasure	maxFm	meanEm	MAE	maxEm	meanFm	wFmeasure	adpEm	adpFm	HCE
TE-P3M-500-P	BiRefNet-portrai--epoch_150	.983	.996	.991	.006	.997	.988	.990	.933	.965	.000

Check the main BiRefNet model repo for more info and how to use it:
https://huggingface.co/ZhengPeng7/BiRefNet/blob/main/README.md

Also check the GitHub repo of BiRefNet for all things you may want:
https://github.com/ZhengPeng7/BiRefNet

Acknowledgement:

Many thanks to @fal for their generous support on GPU resources for training this BiRefNet for portrait matting.

Citation

@article{zheng2024birefnet,
  title={Bilateral Reference for High-Resolution Dichotomous Image Segmentation},
  author={Zheng, Peng and Gao, Dehong and Fan, Deng-Ping and Liu, Li and Laaksonen, Jorma and Ouyang, Wanli and Sebe, Nicu},
  journal={CAAI Artificial Intelligence Research},
  volume = {3},
  pages = {9150038},
  year={2024}
}