paper-with-me

Papers

Font Style Interpolation with Diffusion Models

2024-02-22 · Tetta Kondo, Shumpei Takezaki, Daichi Haraguchi, Seiichi Uchida

Fonts have huge variations in their styles and give readers different impressions. Therefore, generating new fonts is worthy of giving new impressions to readers. In this paper, we employ diffusion models to generate new font styles by interpolating a pair of reference fonts with different styles. More specifically, we propose three different interpolation approaches, image-blending, condition-blending, and noise-blending, with the diffusion models. We perform qualitative and quantitative experimental analyses to understand the style generation ability of the three approaches. According to experimental results, three proposed approaches can generate not only expected font styles but also somewhat serendipitous font styles. We also compare the approaches with a state-of-the-art style-conditional Latin-font generative network model to confirm the validity of using the diffusion models for the style interpolation task.

📄 PDF Abstract BibTeX arXiv:2402.14311

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DiffCJK: Conditional Diffusion Model for High-Quality and Wide-coverage CJK Character Generation

2024-04-08 · Yingtao Tian

Chinese, Japanese, and Korean (CJK), with a vast number of native speakers, have profound influence on society and culture. The typesetting of CJK languages carries a wide range of requirements due to the complexity of t…

Zero-shot Generalization

Automatic Generation of Chinese Handwriting via Fonts Style Representation Learning

2020-03-27 · Fenxi Xiao, Bo Huang, Xia Wu

In this paper, we propose and end-to-end deep Chinese font generation system. This system can generate new style fonts by interpolation of latent style-related embeding variables that could achieve smooth transition betw…

Font GenerationRepresentation Learning

FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning

2023-12-19 · Zhenhua Yang, Dezhi Peng, Yuxin Kong, Yuyi Zhang 외

Automatic font generation is an imitation task, which aims to create a font library that mimics the style of reference images while preserving the content from source images. Although existing font generation methods hav…

Contrastive LearningDenoisingFont GenerationFont Style Transfer+2

VecFusion: Vector Font Generation with Diffusion

2023-12-16 · CVPR 2024 1 · Vikas Thamizharasan, Difan Liu, Shantanu Agarwal, Matthew Fisher 외

We present VecFusion, a new neural architecture that can generate vector fonts with varying topological structures and precise control point positions. Our approach is a cascaded diffusion model which consists of a raste…

Font GenerationVector Graphics

Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models

2024-01-01 · CVPR 2024 1 · Bin Fu, Fanghua Yu, Anran Liu, Zixuan Wang 외

Few-shot font generation (FFG) produces stylized font images with a limited number of reference samples which can significantly reduce labor costs in manual font designs. Most existing FFG methods follow the style-co…

DisentanglementFont GenerationGenerative Adversarial Network