dakshtrehan / white-box-cartoonization Goto Github PK

View Code? Open in Web Editor NEW

Official TensorFlow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations”

Python 0.62% HTML 0.04% CSS 0.04% Jupyter Notebook 99.30%

white-box-cartoonization's Introduction

Join me at www.dakshtrehan.com ; www.linkedin.com/in/dakshtrehan

an-insiders-guide-to-cartoonization-using-machine-learning-ce3648adfe8

Tensorflow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations.

It is implementation of White Box Cartoonization with some minor tweaks.

Use Cases:

Copyright Free image downloaded from PixaBay

How To Use

Inference with Pre-trained Model

Store test images in /test_code/test_images
Run /test_code/cartoonize.py
Results will be saved in /test_code/cartoonized_images

Training from Scratch

Place your training data in corresponding folders in /dataset
Run pretrain.py, results will be saved in /pretrain folder
Run train.py, results will be saved in /train_cartoon folder
Codes are cleaned from production environment and untested
There may be minor problems but should be easy to resolve
Pre-trained VGG_19 model can be found at following url: https://drive.google.com/file/d/1j0jDENjdwxCDb36meP6-u5xDBzmKBOjJ/view?usp=sharing

Datasets

Due to copyright issues, we cannot provide cartoon images used for training.
However, these training datasets are easy to prepare
Scenery images are collected from Shinkai Makoto, Miyazaki Hayao and Hosoda Mamoru films
Clip films into frames and random crop and resize to 256x256
Portrait images are from Kyoto animations and PA Works
We use this repo(https://github.com/nagadomi/lbpcascade_animeface) to detect facial areas
Manual data cleaning will greatly increace both datasets quality

Citation

If you use this code for your research, please cite paper:

@InProceedings{Wang_2020_CVPR, author = {Wang, Xinrui and Yu, Jinze}, title = {Learning to Cartoonize Using White-Box Cartoon Representations}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2020} }