Authors: Wt.Y
Institute: ZJU
(๐ง) corresponding author
2023/08/15
Create repo
- Inpaint wisely with Layer Knowledge and User design
- Layer perception
- Decompose Anything with Simple Interaction
- High Quality Matting and Mask Results
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
- Upload the image and click on it (default:
foreground point
). - Click
Start!
. - Modify
erode_kernel_size
anddilate_kernel_size
for a better trimap (optional).
- [] Matte part
- [] Inpaint part
- [] layer perception part
we find a good matte repo Matte-Anything which part similar as our matte thinking.And we use their repo to do some matte work.
Thanks to their work we can easilier get good output.
@article{decompose_anything,
year={2023}
}