Bilateral Reference for High-Resolution Dichotomous Image Segmentation

An arbitrary shape adaptable BiRefNet for general segmentation.
This model was trained on arbitrary shapes (256x256 ~ 2304x2304) and shows great robustness on inputs with any shape.

Performance

How it looks when compared with BiRefNet-general (fixed 1024x1024 resolution) -- greater than BiRefNet-general and BiRefNet_HR-general on the reserved validation sets (DIS-VD and TE-P3M-500-NP).
The dynamic_XXxXX means this BiRefNet_dynamic model was being tested in various input resolutions for the evaluation.

For performance of different epochs, check the eval_results-xxx folder for it on my google drive.

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 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!

How to use

0. Install Packages:

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

1. Load BiRefNet:

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)

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()
birefnet.half()

def extract_object(birefnet, imagepath):
    # Data settings
    # image_size = (1024, 1024)
    # Since this model was trained on arbitrary shapes (256x256 ~ 2304x2304), the resizing is not necessary.
    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').half()

    # 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()

2. Use inference endpoint locally:

You may need to click the deploy and set up the endpoint by yourself, which would make some costs.

import requests
import base64
from io import BytesIO
from PIL import Image


YOUR_HF_TOKEN = 'xxx'
API_URL = "xxx"
headers = {
	"Authorization": "Bearer {}".format(YOUR_HF_TOKEN)
}

def base64_to_bytes(base64_string):
    # Remove the data URI prefix if present
    if "data:image" in base64_string:
        base64_string = base64_string.split(",")[1]

    # Decode the Base64 string into bytes
    image_bytes = base64.b64decode(base64_string)
    return image_bytes

def bytes_to_base64(image_bytes):
    # Create a BytesIO object to handle the image data
    image_stream = BytesIO(image_bytes)

    # Open the image using Pillow (PIL)
    image = Image.open(image_stream)
    return image

def query(payload):
	response = requests.post(API_URL, headers=headers, json=payload)
	return response.json()

output = query({
	"inputs": "https://hips.hearstapps.com/hmg-prod/images/gettyimages-1229892983-square.jpg",
	"parameters": {}
})

output_image = bytes_to_base64(base64_to_bytes(output))
output_image

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

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).

Go to my GitHub page for BiRefNet codes and the latest updates: https://github.com/ZhengPeng7/BiRefNet :)

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:

Acknowledgement:

• Many thanks to @Freepik for their generous support on GPU resources for training higher resolution BiRefNet models and more of my explorations.
• Many thanks to @fal for their generous support on GPU resources for training better general BiRefNet models.
• Many thanks to @not-lain for his help on the better deployment of our BiRefNet model on HuggingFace.

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}
}