A GAN with elliptical-spiral feature mixing, star-operation blocks, and Sobel edge loss produces more realistic synthetic handwriting and lowers HTR error rates on English and Vietnamese datasets.
DiffusionPen: Towards Controlling the Style of Handwritten Text Generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Handwritten Text Generation (HTG) conditioned on text and style is a challenging task due to the variability of inter-user characteristics and the unlimited combinations of characters that form new words unseen during training. Diffusion Models have recently shown promising results in HTG but still remain under-explored. We present DiffusionPen (DiffPen), a 5-shot style handwritten text generation approach based on Latent Diffusion Models. By utilizing a hybrid style extractor that combines metric learning and classification, our approach manages to capture both textual and stylistic characteristics of seen and unseen words and styles, generating realistic handwritten samples. Moreover, we explore several variation strategies of the data with multi-style mixtures and noisy embeddings, enhancing the robustness and diversity of the generated data. Extensive experiments using IAM offline handwriting database show that our method outperforms existing methods qualitatively and quantitatively, and its additional generated data can improve the performance of Handwriting Text Recognition (HTR) systems. The code is available at: https://github.com/koninik/DiffusionPen.
fields
cs.CV 2years
2026 2representative citing papers
HandwritingAgent generates SVG handwriting strokes via a large reasoning model conditioned on text and a style reference image, matching or exceeding prior generative models on imitation, recognition, multilingual, and math expression tasks without style-specific training.
citing papers explorer
-
SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation
A GAN with elliptical-spiral feature mixing, star-operation blocks, and Sobel edge loss produces more realistic synthetic handwriting and lowers HTR error rates on English and Vietnamese datasets.
-
HandwritingAgent: Language-Driven Handwriting Synthesis in Scalable Vector Space
HandwritingAgent generates SVG handwriting strokes via a large reasoning model conditioned on text and a style reference image, matching or exceeding prior generative models on imitation, recognition, multilingual, and math expression tasks without style-specific training.