AutoPortraitMatting

Tensorflow implementation of Automatic Portrait Matting on paper "Automatic Portrait Segmentation for Image Stylization"

Requirement

Tensorflow
scipy
six
PIL
numpy

Data

mkdir Model_zoo and download http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat

download data from http://xiaoyongshen.me/webpage_portrait/index.html

mkdir data and copy the following folders and files into data/:

images_mask/
images_data/
images_data_crop/
images_tracker/
portraitFCN_data/
portraitFCN+_data/
meanmask.png
testlist.mat
trainlist.mat

Some of the folders data above, will be obtained by additional scripting. To obtain additional data, run the data_download.m and generate_data_file.m respectively

How to run

FCN.py and FCN_puls.py implements the two models in that paper. To train:

` if name == "main": tf.app.run()

pred()

After train, predict:

` if name == "main":

tf.app.run()

  pred()

Datasets

由于shenxiaoyong网站崩溃，提供数据的百度云下载链接 Link: http://pan.baidu.com/s/1dE14537 Password: ndg8 仅供学术交流，如有引用，请通知原作者。

Ackownledge

Thanks for Xiaoyong Shen and his paper

"Deep Automatic Portrait Matting" Xiaoyong Shen, Xin Tao, Hongyun Gao, Chao Zhou, Jiaya Jia. European Conference on Computer Vision (ECCV), 2016

I can't reach the performance in this paper. So please modify it as you want and inform me if any improvement.