Birefnet

🚀 BiRefNet

BiRefNet is a model for high-resolution dichotomous image segmentation, achieving SOTA performance on multiple tasks such as DIS, HRSOD, and COD.

🚀 Quick Start

This repo is the official implementation of "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (CAAI AIR 2024). Visit our GitHub repo: https://github.com/ZhengPeng7/BiRefNet for more details -- codes, docs, and model zoo!

✨ Features

• Multiple Tasks: Achieved the SOTA performance on three tasks (DIS, HRSOD, and COD).
• Multiple Usage Modes: You can use codes and weights from different sources, including HuggingFace and GitHub, or use them locally.

📦 Installation

0. Install Packages:

pip install -qr https://raw.githubusercontent.com/ZhengPeng7/BiRefNet/main/requirements.txt

💻 Usage Examples

Basic Usage

Use codes + weights from HuggingFace

Only use the weights on HuggingFace -- Pro: No need to download BiRefNet codes manually; Con: Codes on HuggingFace might not be latest version (I'll try to keep them always latest).

# Load BiRefNet with weights
from transformers import AutoModelForImageSegmentation
birefnet = AutoModelForImageSegmentation.from_pretrained('ZhengPeng7/BiRefNet', trust_remote_code=True)

Use codes from GitHub + weights from HuggingFace

Only use the weights on HuggingFace -- Pro: codes are always latest; Con: Need to clone the BiRefNet repo from my GitHub.

# Download codes
git clone https://github.com/ZhengPeng7/BiRefNet.git
cd BiRefNet

# Use codes locally
from models.birefnet import BiRefNet

# Load weights from Hugging Face Models
birefnet = BiRefNet.from_pretrained('ZhengPeng7/BiRefNet')

Use codes from GitHub + weights from local space

Only use the weights and codes both locally.

# Use codes and weights locally
import torch
from utils import check_state_dict

birefnet = BiRefNet(bb_pretrained=False)
state_dict = torch.load(PATH_TO_WEIGHT, map_location='cpu')
state_dict = check_state_dict(state_dict)
birefnet.load_state_dict(state_dict)

Advanced Usage

Use the loaded BiRefNet for inference

# Imports
from PIL import Image
import matplotlib.pyplot as plt
import torch
from torchvision import transforms
from models.birefnet import BiRefNet

birefnet = ... # -- BiRefNet should be loaded with codes above, either way.
torch.set_float32_matmul_precision(['high', 'highest'][0])
birefnet.to('cuda')
birefnet.eval()

def extract_object(birefnet, imagepath):
    # Data settings
    image_size = (1024, 1024)
    transform_image = transforms.Compose([
        transforms.Resize(image_size),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ])

    image = Image.open(imagepath)
    input_images = transform_image(image).unsqueeze(0).to('cuda')

    # Prediction
    with torch.no_grad():
        preds = birefnet(input_images)[-1].sigmoid().cpu()
    pred = preds[0].squeeze()
    pred_pil = transforms.ToPILImage()(pred)
    mask = pred_pil.resize(image.size)
    image.putalpha(mask)
    return image, mask

# Visualization
plt.axis("off")
plt.imshow(extract_object(birefnet, imagepath='PATH-TO-YOUR_IMAGE.jpg')[0])
plt.show()

This BiRefNet for standard dichotomous image segmentation (DIS) is trained on DIS-TR and validated on DIS-TEs and DIS-VD.

📚 Documentation

This repo holds the official model weights of "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (CAAI AIR 2024). This repo contains the weights of BiRefNet proposed in our paper, which has achieved the SOTA performance on three tasks (DIS, HRSOD, and COD).

Try our online demos for inference:

• Online Image Inference on Colab:
• Online Inference with GUI on Hugging Face with adjustable resolutions:
• Inference and evaluation of your given weights:

DIS-Sample_1	DIS-Sample_2

🔧 Technical Details

This BiRefNet for standard dichotomous image segmentation (DIS) is trained on DIS-TR and validated on DIS-TEs and DIS-VD.

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

Acknowledgement

• Many thanks to @fal for their generous support on GPU resources for training better BiRefNet models.
• Many thanks to @not-lain for his help on the better deployment of our BiRefNet model on HuggingFace.

Citation

@article{BiRefNet,
  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},
  year={2024}
}