Cross-Domain Image Conversion by CycleDM

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shimotsumagari, Sho, Takezaki, Shumpei, Haraguchi, Daichi, Uchida, Seiichi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911789319454720
author Shimotsumagari, Sho
Takezaki, Shumpei
Haraguchi, Daichi
Uchida, Seiichi
author_facet Shimotsumagari, Sho
Takezaki, Shumpei
Haraguchi, Daichi
Uchida, Seiichi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_02919
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cross-Domain Image Conversion by CycleDM
Shimotsumagari, Sho
Takezaki, Shumpei
Haraguchi, Daichi
Uchida, Seiichi
Computer Vision and Pattern Recognition
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.
title Cross-Domain Image Conversion by CycleDM
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.02919