This repo is the official implementation of "Bilateral Reference for High-Resolution Dichotomous Image Segmentation" (CAAI AIR 2024).
Visit our GitHub repo for more details -- codes, docs, and model zoo!
pip install -qr https://raw.githubusercontent.com/ZhengPeng7/BiRefNet/main/requirements.txt
from transformers import AutoModelForImageSegmentation
birefnet = AutoModelForImageSegmentation.from_pretrained('ZhengPeng7/BiRefNet', trust_remote_code=True)
git clone https://github.com/ZhengPeng7/BiRefNet.git
cd BiRefNet
from models.birefnet import BiRefNet
birefnet = BiRefNet.from_pretrained('ZhengPeng7/BiRefNet')
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)
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)
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()
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):
if "data:image" in base64_string:
base64_string = base64_string.split(",")[1]
image_bytes = base64.b64decode(base64_string)
return image_bytes
def bytes_to_base64(image_bytes):
image_stream = BytesIO(image_bytes)
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.
Try our online demos for inference:
Many thanks to:
@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}
}