mirror
/
MODNet
mirror of https://github.com/ZHKKKe/MODNet.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update README.md

pull/21/head
kezhanghan 2020-12-10 18:50:58 +08:00
parent 0bdc3d1ddf
commit c51ece7232
2 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -23,8 +23,7 @@
## Video Matting Demo ## Video Matting Demo
We provide two real-time portrait video matting demos based on WebCam. We provide two real-time portrait video matting demos based on WebCam.
If you have an Ubuntu system, we recommend you to try the [offline demo](demo/video_matting/README.md) to get a higher *fps*. Otherwise, you can access the [online Colab demo](https://colab.research.google.com/drive/1Pt3KDSc2q7WxFvekCnCLD8P0gBEbxm6J?usp=sharing). If you have an Ubuntu system, we recommend you to try the [offline demo](demo/video_matting) to get a higher *fps*. Otherwise, you can access the [online Colab demo](https://colab.research.google.com/drive/1Pt3KDSc2q7WxFvekCnCLD8P0gBEbxm6J?usp=sharing).
## Image Matting Demo ## Image Matting Demo
@ -38,6 +37,11 @@ It allows you to upload portrait images and predict/visualize/download the alpha
- Release training code (scheduled in **Jan. 2021**) - Release training code (scheduled in **Jan. 2021**)
- Release PPM-100 validation benchmark (scheduled in **Feb. 2021**) - Release PPM-100 validation benchmark (scheduled in **Feb. 2021**)
## License
This project is released under the [Creative Commons Attribution NonCommercial ShareAlike 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode) license.
## Acknowledgement ## Acknowledgement
We thank [City University of Hong Kong](https://www.cityu.edu.hk/) and [SenseTime](https://www.sensetime.com/) for their support to this project. We thank [City University of Hong Kong](https://www.cityu.edu.hk/) and [SenseTime](https://www.sensetime.com/) for their support to this project.

6
demo/video_matting/README.md
View File

@ -1,7 +1,7 @@
## MODNet - WebCam-Based Portrait Video Matting Demo ## MODNet - WebCam-Based Portrait Video Matting Demo
This is a MODNet portrait video matting demo based on WebCam. It will call your local WebCam and display the matting results in real time. This is a MODNet portrait video matting demo based on WebCam. It will call your local WebCam and display the matting results in real time.
### Requirements ### 1. Requirements
The basic requirements for this demo are: The basic requirements for this demo are:
- Ubuntu System - Ubuntu System
- WebCam - WebCam
@ -11,7 +11,7 @@ The basic requirements for this demo are:
**NOTE**: If your device does not satisfy the above conditions, please try our [online Colab demo](https://colab.research.google.com/drive/1Pt3KDSc2q7WxFvekCnCLD8P0gBEbxm6J?usp=sharing). **NOTE**: If your device does not satisfy the above conditions, please try our [online Colab demo](https://colab.research.google.com/drive/1Pt3KDSc2q7WxFvekCnCLD8P0gBEbxm6J?usp=sharing).
### Introduction ### 2. Introduction
We use ~400 unlabeled video clips (divided into ~50,000 frames) downloaded from the internet to perform SOC to adapt MODNet to the video domain. Nonetheless, due to insufficient labeled training data (~3k labeled foregrounds), our model may still make errors in portrait semantics estimation under challenging scenes. Besides, this demo does not currently support the OFD trick, which will be provided soon. We use ~400 unlabeled video clips (divided into ~50,000 frames) downloaded from the internet to perform SOC to adapt MODNet to the video domain. Nonetheless, due to insufficient labeled training data (~3k labeled foregrounds), our model may still make errors in portrait semantics estimation under challenging scenes. Besides, this demo does not currently support the OFD trick, which will be provided soon.
For a better experience, please: For a better experience, please:
@ -21,7 +21,7 @@ For a better experience, please:
* do not be too close or too far from the WebCam * do not be too close or too far from the WebCam
* do not move too fast * do not move too fast
### Run Demo ### 3. Run Demo
We recommend creating a new conda virtual environment to run this demo, as follow: We recommend creating a new conda virtual environment to run this demo, as follow:
1. Clone the MODNet repository: 1. Clone the MODNet repository: