ZhengPeng7/BiRefNet-matting

Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Peng Zheng ^1,4,5,6,  Dehong Gao ²,  Deng-Ping Fan ^1*,  Li Liu ³,  Jorma Laaksonen ⁴,  Wanli Ouyang ⁵,  Nicu Sebe ⁶

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

                 

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

Training Sets:

• P3M-10k (except TE-P3M-500-NP)
• TR-humans
• AM-2k
• AIM-500
• Human-2k (synthesized with BG-20k)
• Distinctions-646 (synthesized with BG-20k)
• HIM2K
• PPM-100

Validation Sets:

• TE-P3M-500-NP

Performance:

Dataset	Method	Smeasure	maxFm	meanEm	MSE	maxEm	meanFm	wFmeasure	adpEm	adpFm	HCE	mBA	maxBIoU	meanBIoU
TE-P3M-500-NP	BiRefNet-matting--epoch_100	.979	.996	.988	.003	.997	.986	.988	.864	.885	.000	.830	.940	.888

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 @freepik for their generous support on GPU resources for training this model!

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}
}