In this branch, we plan to use Segment Anything for human hair/face editing. Right now, we release the tiny demo for hair changing.
Why this project?
🆕 SAM + fashion-edit [Demo Notebook]
Interactively mark part of interests, manipulation enpowered with inpainting model.
Simple notebook interactive annotation playground: Left click to mark positive points[green dot] , right click for negative points[red dot]
SAM + hair-edit
Future interesting works
Some possible avenues for future work ...
The code requires python>=3.8, as well as pytorch>=1.7 and torchvision>=0.8. Please follow the instructions here to install both PyTorch and TorchVision dependencies. Installing both PyTorch and TorchVision with CUDA support is strongly recommended.
Install Segment Anything:
pip install git+https://github.com/facebookresearch/segment-anything.git
or clone the repository locally and install with
git clone git@github.com:facebookresearch/segment-anything.git
cd segment-anything; pip install -e .
The following optional dependencies are necessary for mask post-processing, saving masks in COCO format, the example notebooks, and exporting the model in ONNX format. jupyter is also required to run the example notebooks.
pip install opencv-python pycocotools matplotlib onnxruntime onnx
Install FaceParsing Module:
We use face-parsing.Pytorch for preliminaril face parsing to detect the hair region. We already contain original code in this repo. You can download the pre-trained model and save it in face_parsing_PyTorch/res/cp.
# We use the default(vit-h) model wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth
If you find this project helpful for your research, please consider citing the following BibTeX entry.
@article{kirillov2023segany,
title={Segment Anything},
author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C. and Lo, Wan-Yen and Doll{\'a}r, Piotr and Girshick, Ross},
journal={arXiv:2304.02643},
year={2023}
}
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4