Deepvecfont-v2: Exploiting transformers to synthesize vector fonts with higher quality

Y Wang, Y Wang, L Yu, Y Zhu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Vector font synthesis is a challenging and ongoing problem in the fields of Computer Vision
and Computer Graphics. The recently-proposed DeepVecFont achieved state-of-the-art …

Dualvector: Unsupervised vector font synthesis with dual-part representation

YT Liu, Z Zhang, YC Guo, M Fisher… - Proceedings of the …, 2023 - openaccess.thecvf.com
Automatic generation of fonts can be an important aid to typeface design. Many current
approaches regard glyphs as pixelated images, which present artifacts when scaling and …

Vecfontsdf: Learning to reconstruct and synthesize high-quality vector fonts via signed distance functions

Z Xia, B Xiong, Z Lian - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Font design is of vital importance in the digital content design and modern printing industry.
Developing algorithms capable of automatically synthesizing vector fonts can significantly …

Joint Implicit Neural Representation for High-fidelity and Compact Vector Fonts

CH Chen, YT Liu, Z Zhang, YC Guo… - Proceedings of the …, 2023 - openaccess.thecvf.com
Existing vector font generation approaches either struggle to preserve high-frequency corner
details of the glyph or produce vector shapes that have redundant segments, which hinders …

A survey for graphic design intelligence

D Huang, J Guo, S Sun, H Tian, J Lin, Z Hu… - arXiv preprint arXiv …, 2023 - arxiv.org
Graphic design is an effective language for visual communication. Using complex
composition of visual elements (eg, shape, color, font) guided by design principles and …

QT-Font: High-efficiency Font Synthesis via Quadtree-based Diffusion Models

Y Liu, Z Lian - ACM SIGGRAPH 2024 Conference Papers, 2024 - dl.acm.org
Few-shot font generation (FFG) aims to streamline the manual aspects of the font design
process. Existing models are capable of generating glyph images in the same style of a few …

Kinetic Typography Diffusion Model

S Park, I Bae, S Shin, HG Jeon - European Conference on Computer …, 2025 - Springer
This paper introduces a method for realistic kinetic typography that generates user-preferred
animatable “text content”. We draw on recent advances in guided video diffusion models to …

Path-based Design Model for Constructing and Exploring Alternative Visualisations

J Jackson, PD Ritsos, PWS Butcher… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
We present a path-based design model and system for designing and creating
visualisations. Our model represents a systematic approach to constructing visual …

AmbiGen: Generating Ambigrams from Pre-trained Diffusion Model

B Zhao, R Hanocka, RA Yeh - arXiv preprint arXiv:2312.02967, 2023 - arxiv.org
Ambigrams are calligraphic designs that have different meanings depending on the viewing
orientation. Creating ambigrams is a challenging task even for skilled artists, as it requires …

StyleGAN2-ADA and Real-ESRGAN: Thai font generation with generative adversarial networks

N Nitisukanan, C Boonthaweechok… - Advances in …, 2024 - Springer
Contemporary font design is a labor-intensive process. To address this, we utilize deep
learning, specifically StyleGAN2-ADA and Real-ESRGAN, for automated Thai font …