tuon 146478f00b feat: 增加一次性任务 | 10 달 전 | |
---|---|---|
api | 11 달 전 | |
bin | 10 달 전 | |
configs | 11 달 전 | |
demo | 11 달 전 | |
deploy | 11 달 전 | |
docs | 11 달 전 | |
ppmatting | 11 달 전 | |
tests | 11 달 전 | |
tools | 11 달 전 | |
utils | 11 달 전 | |
.gitignore | 11 달 전 | |
Dockerfile | 10 달 전 | |
Makefile | 10 달 전 | |
README.md | 11 달 전 | |
_log.py | 10 달 전 | |
app.py | 11 달 전 | |
build.sh | 11 달 전 | |
docker-compose.yaml | 11 달 전 | |
install.sh | 11 달 전 | |
main.py | 11 달 전 | |
requirements.txt | 10 달 전 | |
runtest.sh | 11 달 전 | |
start.sh | 11 달 전 | |
task.py | 10 달 전 |
简体中文 | English
人物抠图效果比较好,其它的没有尝试
Image Matting(精细化分割/影像去背/抠图)是指借由计算前景的颜色和透明度,将前景从影像中撷取出来的技术,可用于替换背景、影像合成、视觉特效,在电影工业中被广泛地使用。 影像中的每个像素会有代表其前景透明度的值,称作阿法值(Alpha),一张影像中所有阿法值的集合称作阿法遮罩(Alpha Matte),将影像被遮罩所涵盖的部分取出即可完成前景的分离。
针对高频应用场景 —— 人像抠图,我们训练并开源了高质量人像抠图模型库。根据实际应用场景,大家可以直接部署应用,也支持进行微调训练。
模型库中包括我们自研的高精度PP-Matting模型和轻量级PP-MattingV2模型。
模型 | 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 |
注意:
@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}
}
https://gitee.com/paddlepaddle/PaddleSeg/blob/release/2.8/Matting/docs/quick_start_cn.md