README.md

---
license: other
licence_name: bria-rmbg-1.4
license_link: https://bria.ai/bria-huggingface-model-license-agreement/

tags:
- remove background
- background
- background removal
- Pytorch
- vision
- legal liability

extra_gated_prompt: This model weights by BRIA AI can be obtained after a commercial license is agreed upon. Fill in the form below and we reach out to you.
extra_gated_fields:
  Name: text
  Company/Org name: text
  Org Type (Early/Growth Startup, Enterprise, Academy): text
  Role: text
  Country: text
  Email: text
  By submitting this form, I agree to BRIA’s Privacy policy and Terms & conditions, see links below: checkbox
---

# BRIA Background Removal v1.4 Model Card

RMBG v1.4 is our state-of-the-art background removal model, designed to effectively separate foreground from background in a range of
categories and image types. This model has been trained on a carefully selected dataset, which includes:
general stock images, e-commerce, gaming, and advertising content, making it suitable for various use cases. 
Developed by BRIA AI, RMBG v1.4 is available as an open-source tool for non-commercial use.

[CLICK HERE FOR A DEMO](https://huggingface.co./spaces/briaai/BRIA-RMBG-1.4)
![examples](t4.png)

### Model Description

- **Developed by:** [BRIA AI](https://bria.ai/)
- **Model type:** Background Removal 
- **License:** [bria-rmbg-1.4](https://bria.ai/bria-huggingface-model-license-agreement/)
  - The model is open for non-commercial use.
  - Commercial use is subject to a commercial agreement with BRIA. [Contact Us](https://bria.ai/contact-us) for more information. 

- **Model Description:** BRIA RMBG 1.4 is an saliency segmentation model trained exclusively on a professional-grade dataset.
- **BRIA:** Resources for more information: [BRIA AI](https://bria.ai/)



## Training data
Bria-RMBG model was trained over 12,000 high-quality, high-resolution, manually labeled (pixel-wise accuracy), fully licensed images.
For clarity, we provide our data distribution according to different categories, demonstrating our model’s versatility.

### Distribution of images:

| Category | Distribution |
| -----------------------------------| -----------------------------------:|
| Objects only | 45.11% |
| People with objects/animals | 25.24% |
| People only | 17.35% |
| people/objects/animals with text | 8.52% |
| Text only | 2.52% |
| Animals only | 1.89% |

| Category | Distribution |
| -----------------------------------| -----------------------------------------:|
| Photorealistic | 87.70% |
| Non-Photorealistic | 12.30% |


| Category | Distribution |
| -----------------------------------| -----------------------------------:|
| Non Solid Background | 52.05% |
| Solid Background | 47.95% 


| Category | Distribution |
| -----------------------------------| -----------------------------------:|
| Single main foreground object | 51.42% |
| Multiple objects in the foreground | 48.58% |


## Qualitative Evaluation

![examples](results.png)

- **Inference Time :** 1 sec on Nvidia A10 GPU

## Architecture

RMBG v1.4 is developed on the [IS-Net](https://github.com/xuebinqin/DIS) enhanced with our unique training scheme and proprietary dataset. These modifications significantly improve the model’s accuracy and effectiveness in diverse image-processing scenarios.

## installation
```bash
git clone https://huggingface.co./briaai/RMBG-1.4
cd RMBG-1.4/
pip install -r requirements.txt
```

## Usage

```python
from skimage import io
import torch, os
from PIL import Image
from briarmbg import BriaRMBG
from utilities import preprocess_image, postprocess_image

model_path = f"{os.path.dirname(os.path.abspath(__file__))}/model.pth"
im_path = f"{os.path.dirname(os.path.abspath(__file__))}/example_input.jpg"

net = BriaRMBG()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
net.load_state_dict(torch.load(model_path, map_location=device))
net.eval()    

# prepare input
model_input_size = [1024,1024]
orig_im = io.imread(im_path)
orig_im_size = orig_im.shape[0:2]
image = preprocess_image(orig_im, model_input_size)

if torch.cuda.is_available():
    image=image.cuda()

# inference 
result=net(image)

# post process
result_image = postprocess_image(result[0][0], orig_im_size)

# save result
pil_im = Image.fromarray(result_image)
no_bg_image = Image.new("RGBA", pil_im.size, (0,0,0,0))
orig_image = Image.open(im_path)
no_bg_image.paste(orig_image, mask=pil_im)
no_bg_image.save("example_image_no_bg.png")
```