Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/chingweitseng/general-deep-image-completion
A Deep Image Completion Model for Recovering Various Corrupted Images
https://github.com/chingweitseng/general-deep-image-completion
demo face-completion image-completion inpaint tensorflow
Last synced: about 2 months ago
JSON representation
A Deep Image Completion Model for Recovering Various Corrupted Images
- Host: GitHub
- URL: https://github.com/chingweitseng/general-deep-image-completion
- Owner: chingweitseng
- Created: 2017-08-03T03:04:50.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2018-05-07T14:30:44.000Z (over 6 years ago)
- Last Synced: 2024-07-28T23:22:56.833Z (about 2 months ago)
- Topics: demo, face-completion, image-completion, inpaint, tensorflow
- Language: Python
- Size: 5.5 MB
- Stars: 70
- Watchers: 9
- Forks: 20
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-neural-art - Deep Image Completion - Contains face-completion and general image completion models. Each can complete images with differnet types of corrupted masks like scribbles, lines, dots and texts. (Patching)
README
# General Deep Image Completion with Lightweight cGANs
These are the implementations and simple demo system of my bmvc'17 paper: General Deep Image Completion with Lightweight Conditional Generative Adversarial Network. [\[PDF\]](https://www.dropbox.com/s/e4l19y9ggqqk2yf/0360.pdf?dl=1)[\[SUP\]](https://www.dropbox.com/s/57nzfn7rrlxbzh0/Active%20Papers%20Paper%20360%20%20Supplementary%20File.pdf?dl=1)
The main goal of our paper is to build deep image completion models for recovering various corrupted images, including
- General Image Completion
The objective of this model is to complete images with differnet types of corrupted masks like scribbles, lines, dots and texts.
- Face Completion
This is an extension of our general image completion model that not only tackles the face completion task but also aiming on recovering faces with arbitrary missing regions. We apply a differnet but stronger deep autoencoder structure in this model.
## Training
TBA
## Demo System
We build a simple interactive demonstration of image completion based on Python, OpenCV and TensorFlow on Windows
### Videos (Youtube Links)
[General Image Completion](https://www.youtube.com/watch?v=513xQM4NrxY&feature=youtu.be)
[Face Completion](https://www.youtube.com/watch?v=MWj2kkMDrgY&feature=youtu.be)
### Setups
- Install [Visual Studio Code](https://code.visualstudio.com/): A source code editor (Optional, but highly recommended)
- Follow the guidelines from [TensorFlow](https://www.tensorflow.org/install/install_windows) to install Python 3.5.2 and TensorFlow on Windows
- Install libraries numpy and opencv-python through pip
- Download [face-completion-model](https://drive.google.com/file/d/0BwBvCjzIsl2vZHoxS0RrRm55d1U/view?usp=sharing) and [general-completion-model](https://drive.google.com/file/d/0BwBvCjzIsl2vV3FvZUd0VjdxZE0/view?usp=sharing). Put them into corresponding folders
- Run **demo.py** in general-image-completion or face-completion folder
If you fail to import tensorflow, please refer to [this article](https://github.com/tensorflow/tensorflow/issues/8385) for possible solutions.
### Controls
- Moving mouse to draw scribbles on given images
- Key c: convert corrupted images to completed images
- Key r: resume any scribbles
- Key n: next image
## Citation
@inproceedings{tseng17general-deep,
author = {Ching-Wei Tseng and Hung-Jin Lin and Shang-Hong Lai},
booktitle = {Proceedings of the British Machine Vision Conference ({BMVC})},
title = {General Deep Image Completion with Lightweight Conditional Generative Adversarial Networks},
year = {2017}
}