Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Harryoung 8e150a3228 | 1 year ago | |
---|---|---|
.. | ||
configs | 1 year ago | |
demo | 1 year ago | |
deploy | 1 year ago | |
docs | 1 year ago | |
ppmatting | 1 year ago | |
tools | 1 year ago | |
README.md | 1 year ago | |
README_CN.md | 1 year ago | |
requirements.txt | 1 year ago |
English | 简体中文
Image Matting is the technique of extracting foreground from an image by calculating its color and transparency.
It is widely used in the film industry to replace background, image composition, and visual effects.
Each pixel in the image will have a value that represents its foreground transparency, called Alpha.
The set of all Alpha values in an image is called Alpha Matte.
The part of the image covered by the mask can be extracted to complete foreground separation.
2022.11
2022.07
2022.04
2021.11
For the widely application scenario -- human matting, we have trained and open source the ** high-quality human matting models**.
According the actual application scenario, you can directly deploy or finetune.
The model zoo includes our self developded high accuracy model PP-Matting and lite model PP-MattingV2.
PP-Matting is a high accuracy matting model developded by PaddleSeg, which realizes high-resolution image matting under semantic guidance by the design of Guidance Flow.
For high accuracy, this model is recommended. Two pre-trained models are opened source with 512 and 1024 resolution level.
PP-MattingV2 is a lite matting SOTA model developed by PaddleSeg. It extracts high-level semantc informating by double-pyramid pool and spatial attention,
and uses multi-level feature fusion mechanism for both semantic and detail prediciton.
Model | SAD | MSE | Grad | Conn | Params(M) | FLOPs(G) | FPS | Config File | Checkpoint | Inference Model |
---|---|---|---|---|---|---|---|---|---|---|
PP-MattingV2-512 | 40.59 | 0.0038 | 33.86 | 38.90 | 8.95 | 7.51 | 98.89 | cfg | model | model inference |
PP-Matting-512 | 31.56 | 0.0022 | 31.80 | 30.13 | 24.5 | 91.28 | 28.9 | cfg | model | model inference |
PP-Matting-1024 | 66.22 | 0.0088 | 32.90 | 64.80 | 24.5 | 91.28 | 13.4(1024X1024) | cfg | model | model inference |
PP-HumanMatting | 53.15 | 0.0054 | 43.75 | 52.03 | 63.9 | 135.8 (2048X2048) | 32.8(2048X2048) | cfg | model | model inference |
MODNet-MobileNetV2 | 50.07 | 0.0053 | 35.55 | 48.37 | 6.5 | 15.7 | 68.4 | cfg | model | model inference |
MODNet-ResNet50_vd | 39.01 | 0.0038 | 32.29 | 37.38 | 92.2 | 151.6 | 29.0 | cfg | model | model inference |
MODNet-HRNet_W18 | 35.55 | 0.0035 | 31.73 | 34.07 | 10.2 | 28.5 | 62.6 | cfg | model | model inference |
DIM-VGG16 | 32.31 | 0.0233 | 28.89 | 31.45 | 28.4 | 175.5 | 30.4 | cfg | model | model inference |
Note:
@article{chen2022pp,
title={PP-Matting: High-Accuracy Natural Image Matting},
author={Chen, Guowei and Liu, Yi and Wang, Jian and Peng, Juncai and Hao, Yuying and Chu, Lutao and Tang, Shiyu and Wu, Zewu and Chen, Zeyu and Yu, Zhiliang and others},
journal={arXiv preprint arXiv:2204.09433},
year={2022}
}
飞桨高性能图像分割开发套件,端到端完成从训练到部署的全流程图像分割应用。
https://github.com/PaddlePaddle/PaddleSeg
Python Markdown Text Shell Java other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》