The (Official) PyTorch Implementation of the paper "Deep Extraction of Manga Structural Lines"

Last update: Jan 02, 2023

Overview

MangaLineExtraction_PyTorch

The (Official) PyTorch Implementation of the paper "Deep Extraction of Manga Structural Lines"

Usage

model_torch.py [source folder] [output folder]

Example:

model_torch.py ./pytorchTestCases/ ./pytorchResults/

The model weights (erika.pth)

Please refer to the release section of this repo. Alternatively, you may use this link:

https://www.dropbox.com/s/y8pulix3zs73y62/erika.pth?dl=0

Requirement

Python3
PyTorch (tested on version 1.9)
Python-opencv

How the model is prepared

The PyTorch weights are exactly the same as the theano(!) model. I make some efforts to convert the original weights to the new model and ensure the overall error is less than 1e-3 over the image range from 0-255.

Moreover, the functional PyTorch interface allows easier fine-tuning of this model. You can also take the whole model as a sub-module for your own work (e.g., use the on-the-fly extraction of lines as a structural constraint).

About model training

I really don't want to admit it, but the legacy code looks like some artworks by a two-years old. I will try my best to recover the code to py3 and share the screentone dataset. This won't take long, so please stay tuned.

Go beyond manga

Surprisingly, this model works quite well on color cartoons and other nijigen-like images. Simply load the image as grayscale(by default) and check out the results!

Gallery

I'm glad to share some of the results of this model. Some of the images are copyrighted, I will list the original sources below the images. Feel free to share your creaions with me in the issues section.

©IWAYUU, from the fc2 blog.

BibTeX:

@article{li-2017-deep,
    author   = {Chengze Li and Xueting Liu and Tien-Tsin Wong},
    title    = {Deep Extraction of Manga Structural Lines},
    journal  = {ACM Transactions on Graphics (SIGGRAPH 2017 issue)},
    month    = {July},
    year     = {2017},
    volume   = {36},
    number   = {4},
    pages    = {117:1--117:12},
}

Credit:

Xueting Liu and Tien-Tsin Wong, who contributed this work
Wenliang Wu, who inspired me to port this great thing to PyTorch
Toda Erika, where the project name comes from

Comments

Slow extraction

Hi,

How to speed up the line extraction? Could you elaborate on how to use the on-the-fly extraction?

I'm a bit new to all of this, please patient with me. Thank you!

opened by austin2209 7
'Toda Erika, where the project name comes from'

Maybe this is not something like an issue but is this Toda Erika the Japanese actress? If so, I wonder why this project name comes from her(Just a little curious about this because it seems that the name is not so special. If this question is impolite I apologize first).

opened by MayuOshima 2

Releases(v1)

v1(Sep 5, 2021)

Place this model weight in the root folder of this project to make it work.
Source code(tar.gz)
Source code(zip)
erika.pth(164.78 MB)

The official PyTorch implementation of recent paper - SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training

This repository is the official PyTorch implementation of SAINT. Find the paper on arxiv SAINT: Improved Neural Networks for Tabular Data via Row Atte

284 Dec 21, 2022

Official PyTorch implementation and pretrained models of the paper Self-Supervised Classification Network

Self-Classifier: Self-Supervised Classification Network Official PyTorch implementation and pretrained models of the paper Self-Supervised Classificat

24 Dec 21, 2022

Official Pytorch implementation of paper "Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images"

Reverse_Engineering_GMs Official Pytorch implementation of paper "Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Gener

100 Dec 18, 2022

Official Pytorch Implementation of: "Semantic Diversity Learning for Zero-Shot Multi-label Classification"(2021) paper

Semantic Diversity Learning for Zero-Shot Multi-label Classification Paper Official PyTorch Implementation Avi Ben-Cohen, Nadav Zamir, Emanuel Ben Bar

28 Aug 29, 2022

Official PyTorch implementation of the preprint paper "Stylized Neural Painting", accepted to CVPR 2021.

1.5k Dec 28, 2022

Official Pytorch implementation of ICLR 2018 paper Deep Learning for Physical Processes: Integrating Prior Scientific Knowledge.

Deep Learning for Physical Processes: Integrating Prior Scientific Knowledge: Official Pytorch implementation of ICLR 2018 paper Deep Learning for Phy

47 Nov 6, 2022

This is the official pytorch implementation for the paper: Instance Similarity Learning for Unsupervised Feature Representation.

ISL This is the official pytorch implementation for the paper: Instance Similarity Learning for Unsupervised Feature Representation, which is accepted

19 May 4, 2022

Official PyTorch implementation of the paper "Recycling Discriminator: Towards Opinion-Unaware Image Quality Assessment Using Wasserstein GAN", accepted to ACM MM 2021 BNI Track.

RecycleD Official PyTorch implementation of the paper "Recycling Discriminator: Towards Opinion-Unaware Image Quality Assessment Using Wasserstein GAN

23 Nov 5, 2022

Official PyTorch implementation of the paper: Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting.

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting Official PyTorch implementation of the paper: Improving Graph Neural Net

58 Dec 31, 2022

The (Official) PyTorch Implementation of the paper "Deep Extraction of Manga Structural Lines"

Related tags

Overview

MangaLineExtraction_PyTorch

Usage

The model weights (erika.pth)

Requirement

How the model is prepared

About model training

Go beyond manga

Gallery

BibTeX:

Credit:

You might also like...

The official PyTorch implementation of recent paper - SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training

Official PyTorch implementation and pretrained models of the paper Self-Supervised Classification Network

Official Pytorch implementation of paper "Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images"

Official Pytorch Implementation of: "Semantic Diversity Learning for Zero-Shot Multi-label Classification"(2021) paper

Official PyTorch implementation of the preprint paper "Stylized Neural Painting", accepted to CVPR 2021.

Official Pytorch implementation of ICLR 2018 paper Deep Learning for Physical Processes: Integrating Prior Scientific Knowledge.

This is the official pytorch implementation for the paper: Instance Similarity Learning for Unsupervised Feature Representation.

Official PyTorch implementation of the paper "Recycling Discriminator: Towards Opinion-Unaware Image Quality Assessment Using Wasserstein GAN", accepted to ACM MM 2021 BNI Track.

Official PyTorch implementation of the paper: Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting.

Comments

Slow extraction

'Toda Erika, where the project name comes from'

Releases(v1)

v1(Sep 5, 2021)

Owner

Miaomiao Li

Official PyTorch implementation of Spatial Dependency Networks.

HiPAL: A Deep Framework for Physician Burnout Prediction Using Activity Logs in Electronic Health Records

SeqFormer: a Frustratingly Simple Model for Video Instance Segmentation

DSAC* for Visual Camera Re-Localization (RGB or RGB-D)

The (Official) PyTorch Implementation of the paper "Deep Extraction of Manga Structural Lines"

A Pose Estimator for Dense Reconstruction with the Structured Light Illumination Sensor

Emotion Recognition from Facial Images

OMAMO: orthology-based model organism selection

The source code and dataset for the RecGURU paper (WSDM 2022)

XViT - Space-time Mixing Attention for Video Transformer

Semantic Segmentation Suite in TensorFlow

Supplemental learning materials for "Fourier Feature Networks and Neural Volume Rendering"

Sarus implementation of classical ML models. The models are implemented using the Keras API of tensorflow 2. Vizualization are implemented and can be seen in tensorboard.

SCU OlympicsRunning Baseline

Simple data balancing baselines for worst-group-accuracy benchmarks.

Deep motion transfer

AI drive app that can help user become beautiful.

Code and real data for the paper "Counterfactual Temporal Point Processes", available at arXiv.

Text-to-Image generation

Multivariate Time Series Forecasting with efficient Transformers. Code for the paper "Long-Range Transformers for Dynamic Spatiotemporal Forecasting."