Stable Video Matting with Consistent Memory Propagation (MODIFIED FOR WINDOWS)

¹S-Lab, Nanyang Technological University  ²SenseTime Research, Singapore 

MatAnyone is a practical human video matting framework supporting target assignment, with stable performance in both semantics of core regions and fine-grained boundary details.

🎥 For more visual results, go checkout our project page

---

📮 Update

• [2025.02.19] Modified python to better function on windows
• [2025.02] Release inference codes and gradio demo 🤗
• [2025.02] This repo is created.

🔧 Installation

1. Clone Repo

   git clone https://github.com/pq-yang/MatAnyone
   cd MatAnyone

2. Create Environment and Install Dependencies

   Run "run app.bat" script in the "hugging_face" folder.
   
   Note: This needs Python 3.12 installed along with CUDA 12

🔥 Inference

Download Model

Download our pretrained model from MatAnyone v1.0.0 to the pretrained_models folder (pretrained model can also be automatically downloaded during the first inference).

The directory structure will be arranged as:

pretrained_models
   |- matanyone.pth

🎪 Interactive Demo

By launching, an interactive interface will appear as follow:

📑 Citation

 @InProceedings{yang2025matanyone,
     title     = {{MatAnyone}: Stable Video Matting with Consistent Memory Propagation},
     author    = {Yang, Peiqing and Zhou, Shangchen and Zhao, Jixin and Tao, Qingyi and Loy, Chen Change},
     booktitle = {arXiv preprint arXiv:2501.14677},
     year      = {2025}
     }