DG-Font: Deformable Generative Networks for Unsupervised Font Generation

04/07/2021
by   Yangchen Xie, et al.
0

Font generation is a challenging problem especially for some writing systems that consist of a large number of characters and has attracted a lot of attention in recent years. However, existing methods for font generation are often in supervised learning. They require a large number of paired data, which is labor-intensive and expensive to collect. Besides, common image-to-image translation models often define style as the set of textures and colors, which cannot be directly applied to font generation. To address these problems, we propose novel deformable generative networks for unsupervised font generation (DGFont). We introduce a feature deformation skip connection (FDSC) which predicts pairs of displacement maps and employs the predicted maps to apply deformable convolution to the low-level feature maps from the content encoder. The outputs of FDSC are fed into a mixer to generate the final results. Taking advantage of FDSC, the mixer outputs a high-quality character with a complete structure. To further improve the quality of generated images, we use three deformable convolution layers in the content encoder to learn style-invariant feature representations. Experiments demonstrate that our model generates characters in higher quality than state-of-art methods. The source code is available at https://github.com/ecnuycxie/DG-Font.

READ FULL TEXT
research
12/30/2022

DGFont++: Robust Deformable Generative Networks for Unsupervised Font Generation

Automatic font generation without human experts is a practical and signi...
research
08/03/2023

Revisiting Deformable Convolution for Depth Completion

Depth completion, which aims to generate high-quality dense depth maps f...
research
06/22/2021

Fine-Tuning StyleGAN2 For Cartoon Face Generation

Recent studies have shown remarkable success in the unsupervised image t...
research
07/21/2020

Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder

Novel view synthesis often needs the paired data from both the source an...
research
05/21/2020

Few-shot Compositional Font Generation with Dual Memory

Generating a new font library is a very labor-intensive and time-consumi...
research
06/16/2022

An Improved Normed-Deformable Convolution for Crowd Counting

In recent years, crowd counting has become an important issue in compute...
research
03/23/2021

DeFLOCNet: Deep Image Editing via Flexible Low-level Controls

User-intended visual content fills the hole regions of an input image in...

Please sign up or login with your details

Forgot password? Click here to reset