#
2024/05/04
Matte Anything has been accepted by the Journal of Image and Vision Computing!2024/01/02
Now you can get alpha materials with MatAny! Check it now!2023/07/01
We release a new version that enables text input and transparency correction!2023/06/08
We release arxiv tech report! 2023/06/08
We release source codes of Matte Anything!The program is still in progress. You can try the early version first! Thanks for your attention. If you like Matte Anything, you may also like its previous foundation work ViTMatte.
#
MatAny could get matting results as RGBA images. It will be saved into your_demos/your_demo.png
. You can specify the saving name of it in our UI. We hope MatAny could help.
We propose Matte Anything (MatAny), an interactive natural image matting model. It could produce high-quality alpha-matte with various simple hints. The key insight of MatAny is to generate pseudo trimap automatically with contour and transparency prediction. We leverage task-specific vision models to enhance the performance of natural image matting.
Try our Matte Anything with our web-ui!
Install Segment Anything Models as following:
pip install git+https://github.com/facebookresearch/segment-anything.git
Install ViTMatte as following:
python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'
pip install -r requirements.txt
Install GroundingDINO as following:
cd Matte-Anything
git clone https://github.com/IDEA-Research/GroundingDINO.git
cd GroundingDINO
pip install -e .
Download pretrained models SAM_vit_h, ViTMatte_vit_b, and GroundingDINO-T. Put them in ./pretrained
python matte_anything.py
foreground point
).Start!
.erode_kernel_size
and dilate_kernel_size
for a better trimap (optional).https://github.com/hustvl/Matte-Anything/assets/74295796/dfe051c2-b5d1-442d-9eff-cd1fcfd1f51b
Visualization of SAM and MatAny on real-world data from AM-2K and P3M-500 .
Visualization of SAM and MatAny on Composition-1k
Our repo is built upon Segment Anything, GroundingDINO, and ViTMatte. Thanks to their work.
@article{yao2024matte,
title={Matte anything: Interactive natural image matting with segment anything model},
author={Yao, Jingfeng and Wang, Xinggang and Ye, Lang and Liu, Wenyu},
journal={Image and Vision Computing},
pages={105067},
year={2024},
publisher={Elsevier}
}