DeepMosaics

You can use it to automatically remove the mosaics in images and videos, or add mosaics to them.
This porject based on ‘semantic segmentation’ and ‘Image-to-Image Translation’.

中文版

More example

origin	auto add mosaic	auto clean mosaic

Compared with DeepCreamPy

mosaic image	DeepCreamPy	ours

Notice

The code do not include the part of training, I will finish it in my free time.

Run DeepMosaics

You can either run DeepMosaics via pre-built binary package or from source.

Pre-built binary package

For windows, we bulid a GUI version for easy test.
Download this version via [Google Drive] [百度云,提取码1x0a]

Attentions:

Require Windows_x86_64, Windows10 is better.
Different pre-trained models are suitable for different effects.
Run time depends on computer performance.
If output video cannot be played, you can try with potplayer.
GUI version update slower than source.

Run from source

Prerequisites

Linux, Mac OS, Windows
Python 3.6+
ffmpeg 3.4
Pytorch 1.0+ (Old version codes)
CPU or NVIDIA GPU + CUDA CuDNN

Dependencies

This code depends on opencv-python, torchvision available via pip install.

Clone this repo

git clone https://github.com/HypoX64/DeepMosaics
cd DeepMosaics

Get pre_trained models and test video

You can download pre_trained models and test video and replace the files in the project.
[Google Drive] [百度云,提取码7thu]

Simple example

Add Mosaic (output video will save in './result')

python3 deepmosaic.py

Clean Mosaic (output video will save in './result')

python3 deepmosaic.py --mode clean --model_path ./pretrained_models/clean_hands_unet_128.pth --media_path ./result/hands_test_AddMosaic.mp4

More parameters

If you want to test other image or video, please refer to this file. [options.py]

Acknowledgments

This code borrows heavily from [pytorch-CycleGAN-and-pix2pix] [Pytorch-UNet][pix2pixHD].

freemindhack / DeepMosaics