Toon-it

This is a web app to make real world images to cartoon like artist drawn images. This work is based on 2020 CVPR paper: Learning to Cartoonize Using White-box Cartoon Representations and is Licensed under the CC BY-NC-SA 4.0 license, due to use of citated code of original research.

Technologies used: Tensorflow, Flask, HTML

Installation

python3 -m pip install -r requirements.txt
python3 main.py
(tada webapp is running in =>

localhost:5000/)

You can look at your demo here.

This webapp was featured in top 5 📈 trending projects in MadeWithML

[CVPR2020]Learning to Cartoonize Using White-box Cartoon Representations

project page | paper | twitter | zhihu | bilibili

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

Use cases

Scenery

Food

Indoor Scenes

People

More Images Are Shown In The Supplementary Materials

Prerequisites

• Training code: Linux or Windows
• NVIDIA GPU + CUDA CuDNN for performance
• Inference code: Linux, Windows and MacOS

How To Use

Installation

• Assume you already have NVIDIA GPU and CUDA CuDNN installed
• Install tensorflow-gpu, we tested 1.12.0 and 1.13.0rc0
• Install scikit-image==0.14.5, other versions may cause problems

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

Train

• 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
• Pretrained 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

Acknowledgement

We are grateful for the help from Lvmin Zhang and Style2Paints Research

• Creating tflite model

License

This project is Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode), due to use of citated code for our research.

Citation

If you use this code for your research, please cite our 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} }