Awesome

<img src="demo/o_e92b90fc.gif" width="33%"><img src="demo/o_2749e288.gif" width="33%"><img src="demo/o_87e77b32.gif" width="33%">

<h3><strong><i>📆 News</i></strong></h3>

[2021-11-17]: Release the code for training and dataset processing in this code-base page.

[2021-10-02]: Publish the network, the inference code and the pretrained models in this code-base page.

[2021-07-16]: Publish the validation dataset AIM-500. Please follow the readme.txt for details.

Dataset	<p>Dataset Link<br>(Google Drive)</p>	<p>Dataset Link<br>(Baidu Wangpan 百度网盘)</p>	Dataset Release Agreement
<strong>AIM-500</strong>	Link	Link (pw: 0l69)	Agreement (MIT License)

Introduction

Network - AimNet

We propose the methods consist of:

• <strong>Improved Backbone for Matting</strong>: an advanced max-pooling version of ResNet-34, serves as the backbone for the matting network, pretrained on ImageNet;

• <strong>Unified Semantic Representation</strong>: a type-wise semantic representation to replace the traditional trimaps;

• <strong>Guided Matting Process</strong>: an attention based mechanism to guide the matting process by leveraging the learned semantic features from the semantic decoder to focus on extracting details only within transition area.

The backbone pretrained on ImageNet, the model pretrained on DUTS dataset, and the model pretrained on synthetic matting dataset will be released soon.

AIM-500

We propose <strong>AIM-500</strong> (Automatic Image Matting-500), the first natural image matting test set, which contains 500 high-resolution real-world natural images from all three types (SO, STM, NS), many categories, and the manually labeled alpha mattes. Some examples and the amount of each category are shown below. The <strong>AIM-500</strong> dataset is <strong>published</strong> now, can be downloaded directly from Google Drive or Baidu Wangpan (pw: 0l69). Please make sure that you have read the agreement and agreed to it.

Results on AIM-500

We test our network on different types of images in AIM-500 and compare with previous SOTA methods, the results are shown below. The code for testing and evaluating on AIM-500 can be checked in this code-base page.

Inference Code - How to Test on Your Images

Here we provide the procedure of testing on sample images by our pretrained model:

1. Setup environment following this instruction page;

2. Insert the path REPOSITORY_ROOT_PATH in the file core/config.py;

3. Download the pretrained AimNet model from here (Google Drive|Baidu Wangpan (pw: evik)) and unzip to the folder models/pretrained/;

4. Save your sample images in folder samples/original/.;

5. Setup parameters in the file scripts/test_samples.sh and run by:

   chmod +x scripts/test_samples.sh

   scripts/test_samples.sh;

6. The results of alpha matte and transparent color image will be saved in folder samples/result_alpha/. and samples/result_color/..

We show some sample images from the internet, the predicted alpha mattes, and their transparent results as below. We use the pretrained model from section <a href="#network-aimnet">Network</a> with Hybrid (1/2 & 1/4) test strategy.

<img src="samples/original/1.jpg" width="33%"><img src="samples/result_alpha/1.png" width="33%"><img src="samples/result_color/1.png" width="33%"><img src="samples/original/2.jpg" width="33%"><img src="samples/result_alpha/2.png" width="33%"><img src="samples/result_color/2.png" width="33%"><img src="samples/original/3.jpg" width="33%"><img src="samples/result_alpha/3.png" width="33%"><img src="samples/result_color/3.png" width="33%">

Statement

If you are interested in our work, please consider citing the following:

@inproceedings{ijcai2021-111,
  title     = {Deep Automatic Natural Image Matting},
  author    = {Li, Jizhizi and Zhang, Jing and Tao, Dacheng},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Zhi-Hua Zhou},
  pages     = {800--806},
  year      = {2021},
  month     = {8},
  note      = {Main Track}
  doi       = {10.24963/ijcai.2021/111},
  url       = {https://doi.org/10.24963/ijcai.2021/111},
}

This project is under the MIT license. For further questions, please contact <strong><i>Jizhizi Li</i></strong> at jili8515@uni.sydney.edu.au.

Relevant Projects

<a href="https://github.com/ViTAE-Transformer/ViTAE-Transformer-Matting"><img src="https://shields.io/badge/-A_list_of_our_works_in_matting-9cf?style=for-the-badge"></a>

[1] <strong>Privacy-Preserving Portrait Matting, ACM MM, 2021</strong> | Paper | Github <br><em>     Jizhizi Li^∗, Sihan Ma^∗, Jing Zhang, and Dacheng Tao</em>

[2] <strong>Bridging Composite and Real: Towards End-to-end Deep Image Matting, IJCV, 2022 </strong> | Paper | Github <br><em>     Jizhizi Li^∗, Jing Zhang^∗, Stephen J. Maybank, Dacheng Tao</em>

[3] <strong>Referring Image Matting, CVPR, 2023</strong> | Paper | Github <br><em>     Jizhizi Li, Jing Zhang, and Dacheng Tao</em>

[4] <strong>Rethinking Portrait Matting with Privacy Preserving, IJCV, 2023</strong> | Paper | Github <br><em>     Sihan Ma^∗, Jizhizi Li^∗, Jing Zhang, He Zhang, Dacheng Tao</em>

[5] <strong>Deep Image Matting: A Comprehensive Survey, ArXiv, 2023</strong> | Paper | Github <br><em>     Jizhizi Li, Jing Zhang, and Dacheng Tao</em>