DeepVecFont

This is the official Pytorch implementation of the paper:

Yizhi Wang and Zhouhui Lian. DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning. SIGGRAPH 2021 Asia. 2021.

Paper: arxiv

Demo

Few-shot generation

Given a few vector glyphs of a font as reference, our model generates the full vector font:

Input glyphs:

Input glyphs:

Input glyphs:

Installation

Requirement

• python 3.9
• Pytorch 1.9 (it may work on some lower versions, but not tested)

Please use Anaconda to build the environment:

conda create -n dvf python=3.9
source activate dvf

Install pytorch via the instructions.

Install diffvg

We utilize diffvg to refine our generated vector glyphs in the testing phase. Please go to https://github.com/BachiLi/diffvg see how to install it.

Data and Pretrained-model

Dataset

• The Vector Font dataset Download links: Google Drive

Please download the vecfont_dataset dir and put it under ./data/. (This dataset is a subset from SVG-VAE, ICCV 2019. We will release more information about how to create from your own data.)

• The mean and stdev files Download links: Google Drive

Please Download them and put it under ./data/.

Pretrained model

• The Neural Rasterizer Download links: Google Drive

Please download the dvf_neural_raster dir and put it under ./experiments/.

• The Image Super-resolution model Download links: Google Drive.

Please download the image_sr dir and put it under ./experiments/. Note that recently we switched from Tensorflow to Pytorch, we may update the models that have better performances.

• The Main model Download links: [will be uploaded soon].

Training and Testing

To train our main model, run

python main.py --mode train --experiment_name dvf --model_name main_model

The configurations can be found in options.py.

To test our main model, run

python test_sf.py --mode test --experiment_name dvf --model_name main_model --test_epoch 1500 --batch_size 1 --mix_temperature 0.0001 --gauss_temperature 0.01

This will output the synthesized fonts without refinements. Note that batch_size must be set to 1.

To refinement the vector glyphs, run

python refinement.mp.py --experiment_name dvf --fontid 14 --candidate_nums 20 

where the fontid denotes the index of testing font.

We have pretrained the neural rasterizer and image super-resolution model. If you want to train them yourself:

To train the neural rasterizer:

python train_nr.py --mode train --experiment_name dvf --model_name neural_raster

To train the image super-resolution model:

python train_sr.py --mode train --name image_sr