Semantic-Image-Inpainting-face-inpainting-TensorFlow
Semantic-Image-Inpainting-face-inpainting-TensorFlow copied to clipboard
Simplely implement the paper 'Semantic Image Inpainting with Deep Generative Models' by TensorFlow
Semantic-Image-Inpainting
Simplely implement the paper 'Semantic Image Inpainting with Deep Generative Models'
Indroduction
This code simplely implement the paper Semantic Image Inpainting with Deep Generative Models. The results of the paper have good results of face inpainting.
Method
The method of the paper is divided into two stages,
First, train the DCGAN to get the pretrained model(generator, discriminator).
Second, use the pretrained model of DCGAN from the first stage to train the input(z) of the generator, a little similar with neural style transfer.
Python packages
======================
tensorflow 1.4.0
python 3.5
pillow
numpy
scipy
======================
Dataset
In the first stage, we select the CelebA as the dataset of the DCGAN to get the pretrained model, and remain 1000 as test data in the second stage.
Results
Raw | incompleted | completed |
---|---|---|
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
Inpainting |
---|
![]() |
![]() |
![]() |
![]() |
col 1: raw image, col 2: incompleted image, col 3: generated image by generator, col 4: completed image