BiRefNet.top

This project is an online demonstration website for our team's solution to the topic "General Scene Intelligent High-Precision Parsing Innovative Application based on Ascend MindSpore" in the China International College Students' Innovation Competition, industry proposition track.

On this website, you can freely experience our solution, which may be the most powerful commercially available image matting model. However, it is not limited to this; it has much broader applications. For more details, please visit our website.

Home:

Demo:

BiRefNet

Bilateral Reference for High-Resolution Dichotomous Image Segmentation (CAAI AIR 2024).

Authors: Peng Zheng, Dehong Gao, Deng-Ping Fan, Li Liu, Jorma Laaksonen, Wanli Ouyang, & Nicu Sebe.

[arXiv] [code] [stuff] [中文版]

Our BiRefNet has achieved SOTA on many similar HR tasks:

DIS:

Figure of Comparison on Papers with Codes (by the time of this work):

COD:

Figure of Comparison on Papers with Codes (by the time of this work):

HRSOD:

Figure of Comparison on Papers with Codes (by the time of this work):

BiRefNet vs Adobe Photoshop vs Adobe Express

How it works

It uses a DIS model called BiRefNet on Replicate to segment images with high accuracy. This application gives you the ability to upload any photo, which will send it through this DIS Model using a Next.js API route, and return your segmented photo.

Running Locally

If you want to start your project based on our code, you can follow the steps outlined below. We would also like to introduce an excellent project🥰🥰🥰——RestorePhoto.io, which served as the foundation for our project.

We have added many personalized components and content to better showcase our model. During this process, we encapsulated the code to aid in understanding the framework and components for personalized modifications.

Cloning the repository the local machine.

git clone

Creating a account on Replicate to get an API key.

1. Go to Replicate to make an account.
2. Click on your profile picture in the top right corner, and click on "Dashboard".
3. Click on "Account" in the navbar. And, here you can find your API token, copy it.

Storing API key in .env file.

Create a file in root directory of project with env. And store your API key in it, as shown in the .example.env file.

If you'd also like to do rate limiting, create an account on UpStash, create a Redis database, and populate the two environment variables in .env as well. If you don't want to do rate limiting, you don't need to make any changes.

Installing the dependencies.

npm install

Running the application.

Then, run the application in the command line and it will be available at http://localhost:3000.

npm run dev

Powered by

This example is powered by the following 3 services:

• Replicate (Our replicate API)
• Upload (storage)
• Vercel (hosting, serverless functions, analytics)

Thanks🥰🥰🥰

• RestorePhotos.io(code basic)