Cross-Domain Image Conversion by CycleDM
Not on the map. Why?
Abstract (arXiv)
The purpose of this paper is to enable the conversion between machine-printed character images (i.e., font images) and handwritten character images through machine learning. For this purpose, we propose a novel unpaired image-to-image domain conversion method, CycleDM, which incorporates the concept of CycleGAN into the diffusion model. Specifically, CycleDM has two internal conversion models that bridge the denoising processes of two image domains. These conversion models are efficiently trained without explicit correspondence between the domains. By applying machine-printed and handwritten character images to the two modalities, CycleDM realizes the conversion between them. Our experiments for evaluating the converted images quantitatively and qualitatively found that ours performs better than other comparable approaches.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 5 Mar 2024.
Builds on
26 of 37 references.
References · 26
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2017Improved Training of Wasserstein GANscited by 2,235
- 2017Adversarial Discriminative Domain Adaptationcited by 1,311
- 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
- 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
- 2017Image to Image Translation for Domain Adaptationcited by 171
- 2021UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Modelscited by 133
14 more
- 2022Semantic Image Synthesis via Diffusion Modelscited by 132
- 2023Word-As-Image for Semantic Typographycited by 63
- 2023Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfercited by 59
- 2023FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learningcited by 48
- 2022DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylizationcited by 45
- 2022Diff-Font: Diffusion Model for Robust One-Shot Font Generationcited by 40
- 2023ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priorscited by 40
- 2023DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Modelscited by 27
- 2023DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusioncited by 26
- 2023SGDiff: A Style Guided Diffusion Model for Fashion Synthesiscited by 20
- 2023WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Modelscited by 15
- 2023Zero-shot Generation of Training Data with Denoising Diffusion Probabilistic Model for Handwritten Chinese Character Recognitioncited by 10
- 2022Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image Generationcited by 9
- 2023Ambigram Generation by A Diffusion Modelcited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025CycleDiff: Cycle Diffusion Models for Unpaired Image-to-image Translation
- 2023DECDM: Document Enhancement using Cycle-Consistent Diffusion Models
- 2025A Diffusion Model Translator for Efficient Image-to-Image Translation
- 2023CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation
- 2022BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models
- 2025Generalized Denoising Diffusion Codebook Models (gDDCM): Tokenizing images using a pre-trained diffusion model
- 2024Unified Image Restoration and Enhancement: Degradation Calibrated Cycle Reconstruction Diffusion Model
- 2026Image Tokenizers Should Be Trained Between Images