# Zero-shot Generation of Training Data with Denoising Diffusion Probabilistic Model for Handwritten Chinese Character Recognition arXiv: https://arxiv.org/abs/2305.15660 ยท HTML: https://mlsanity.com/paper/2305.15660/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. - Builds on 40 of its 55 references that are in the map. - First posted on arXiv 25 May 2023. ## Placed in - Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/) ## Builds on (most cited first, 30 of 40) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020) - [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020) - [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021) - [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015) - [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022) - [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022) - [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022) - [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019) - [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021) - [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021) - [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016) - [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018) - [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017) - [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021) - [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021) - [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022) - [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020) - [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022) - [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013) - [Pretraining is All You Need for Image-to-Image Translation](https://mlsanity.com/paper/2205.12952/) (2022) - [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021) - [DG-Font: Deformable Generative Networks for Unsupervised Font Generation](https://mlsanity.com/paper/2104.03064/) (2021) - [Separating Style and Content for Generalized Style Transfer](https://mlsanity.com/paper/1711.06454/) (2017) - [Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning](https://mlsanity.com/paper/1910.04987/) (2019) - [Few-shot Font Generation with Localized Style Representations and Factorization](https://mlsanity.com/paper/2009.11042/) (2020) - [Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition](https://mlsanity.com/paper/2106.11613/) (2021) - [Diffusion models for Handwriting Generation](https://mlsanity.com/paper/2011.06704/) (2020) ## Built on by (most cited first, 10 of 10) - [GlyphControl: Glyph Conditional Control for Visual Text Generation](https://mlsanity.com/paper/2305.18259/) (2023) - [Visual Text Generation in the Wild](https://mlsanity.com/paper/2407.14138/) (2024) - [DiffusionPen: Towards Controlling the Style of Handwritten Text Generation](https://mlsanity.com/paper/2409.06065/) (2024) - [Improving Handwritten OCR with Training Samples Generated by Glyph Conditional Denoising Diffusion Probabilistic Model](https://mlsanity.com/paper/2305.19543/) (2023) - [TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition](https://mlsanity.com/paper/2412.01137/) (2024) - [Diff-Oracle: Deciphering Oracle Bone Scripts with Controllable Diffusion Model](https://mlsanity.com/paper/2312.13631/) (2023) - [MetaScript: Few-Shot Handwritten Chinese Content Generation via Generative Adversarial Networks](https://mlsanity.com/paper/2312.16251/) (2023) - [DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting Generation](https://mlsanity.com/paper/2509.23624/) (2025) - [Cross-Domain Image Conversion by CycleDM](https://mlsanity.com/paper/2403.02919/) (2024) - [AnyArtisticGlyph: Multilingual Controllable Artistic Glyph Generation](https://mlsanity.com/paper/2504.04743/) (2025) ## Abstract (arXiv) There are more than 80,000 character categories in Chinese while most of them are rarely used. To build a high performance handwritten Chinese character recognition (HCCR) system supporting the full character set with a traditional approach, many training samples need be collected for each character category, which is both time-consuming and expensive. In this paper, we propose a novel approach to transforming Chinese character glyph images generated from font libraries to handwritten ones with a denoising diffusion probabilistic model (DDPM). Training from handwritten samples of a small character set, the DDPM is capable of mapping printed strokes to handwritten ones, which makes it possible to generate photo-realistic and diverse style handwritten samples of unseen character categories. Combining DDPM-synthesized samples of unseen categories with real samples of other categories, we can build an HCCR system to support the full character set. Experimental results on CASIA-HWDB dataset with 3,755 character categories show that the HCCR systems trained with synthetic samples perform similarly with the one trained with real samples in terms of recognition accuracy. The proposed method has the potential to address HCCR with a larger vocabulary.