https://github.com/cyberagentailab/multipalette

Implementation of Color Recommendation for Vector Graphic Documents based on Multi-Palette Representation, WACV 2023

https://github.com/cyberagentailab/multipalette

Science Score: 23.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
    Found 1 DOI reference(s) in README
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (8.4%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Implementation of Color Recommendation for Vector Graphic Documents based on Multi-Palette Representation, WACV 2023

Basic Info
  • Host: GitHub
  • Owner: CyberAgentAILab
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 8.76 MB
Statistics
  • Stars: 6
  • Watchers: 0
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created almost 4 years ago · Last pushed almost 3 years ago

https://github.com/CyberAgentAILab/multipalette/blob/main/

# Color recommendation for vector graphic documents 

Official implementation of [Color Recommendation for Vector Graphic Documents based on Multi-Palette Representation, WACV 2023](https://openaccess.thecvf.com/content/WACV2023/papers/Qiu_Color_Recommendation_for_Vector_Graphic_Documents_Based_on_Multi-Palette_Representation_WACV_2023_paper.pdf)

![Overview_image](docs/overview.png)

## Prerequisites

- Python:3.8
- Poetry: 1.2.*

## Setup

Install requirements and run jupyter.

```
poetry install
poetry run jupyter lab
```

## Quick demo

`notebooks/recomm_colors.ipynb`: recommend colors for multiple palettes in a design
- Trained model of color prediction are in trained_models/.
- Json files for test are pre-created in data/model_test_input/crello_samples/.

You can train a color model on a notebook `notebooks/train_model.ipynb`. We recommended GPU resources to train this model (e.g. Tesla T4 * 1).
You can also create a json file for test from crello dataset on a notebook `notebooks/create_json_file.ipynb`.

## Data

`data/training_data/metadata_colors`: extracted color palettes for Image-SVG-Text elements from [Crello-dataset-v1](https://storage.googleapis.com/ailab-public/canvas-vae/crello-dataset-v1.zip) ([the lastest Crello-dataset](https://github.com/CyberAgentAILab/canvas-vae/blob/main/docs/crello-dataset.md))

`data/training_data/data_bert/data_color`: color corpus of train, validation, and test dataset, and color vocabulary from train dataset

`data/trained_models`: trained model for color recommendation

`model_test_input`: json sample files for testing the results of color recommendation

## Citation

```bibtex
@misc{Qiu_2022,
  author = {Qiu Qianru, Wang Xueting, Otani Mayu, and Iwazaki Yuki},
  title = {Color Recommendation for Vector Graphic Documents based on Multi-Palette Representation},  
  doi = {10.48550/ARXIV.2209.10820},  
  url = {https://arxiv.org/abs/2209.10820},  
  year = {2022},
}
```

Owner

  • Name: CyberAgent AI Lab
  • Login: CyberAgentAILab
  • Kind: organization
  • Location: Japan

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Dependencies

poetry.lock pypi
  • 179 dependencies
pyproject.toml pypi
  • ipycanvas ^0.13.1
  • jupyterlab ^3.4.7
  • jupyterlab-requirements ^0.13.0
  • matplotlib ^3.5.3
  • opencv-python ^4.6.0
  • pandas ^1.4.4
  • python ^3.8
  • scikit-learn ^1.1.2