VariGAN: Enhancing Image Style Transfer via UNet Generator, Depthwise Discriminator, and LPIPS Loss in Adversarial Learning Framework

Image style transfer is a challenging task that has gained significant attention in recent years due to its growing complexity. Training is typically performed using paradigms offered by GAN-based image style transfer networks. Cycle-based training methods provide an approach for handling unpaired d...

Full description

Saved in:
Bibliographic Details
Main Authors: Dawei Guan, Xinping Lin, Haoyi Zhang, Hang Zhou
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/9/2671
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850279184889282560
author Dawei Guan
Xinping Lin
Haoyi Zhang
Hang Zhou
author_facet Dawei Guan
Xinping Lin
Haoyi Zhang
Hang Zhou
author_sort Dawei Guan
collection DOAJ
description Image style transfer is a challenging task that has gained significant attention in recent years due to its growing complexity. Training is typically performed using paradigms offered by GAN-based image style transfer networks. Cycle-based training methods provide an approach for handling unpaired data. Nevertheless, achieving high transfer quality remains a challenge with these methods due to the simplicity of the employed network. The purpose of this research is to present <i>VariGAN</i>, a novel approach that incorporates three additional strategies to optimize GAN-based image style transfer: (1) Improving the quality of transferred images by utilizing an effective UNet generator network in conjunction with a context-related feature extraction module. (2) Optimizing the training process while reducing dependency on the generator through the use of a depthwise discriminator. (3) Introducing LPIPS loss to further refine the loss function and enhance the overall generation quality of the framework. Through a series of experiments, we demonstrate that the <i>VariGAN</i> backbone exhibits superior performance across diverse content and style domains. <i>VariGAN</i> improved class IoU by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>236</mn><mo>%</mo></mrow></semantics></math></inline-formula> and participant identification by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>195</mn><mo>%</mo></mrow></semantics></math></inline-formula> compared to <i>CycleGAN</i>.
format Article
id doaj-art-b5a1d587c9274e8f924a1f0cd5db87d2
institution OA Journals
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-b5a1d587c9274e8f924a1f0cd5db87d22025-08-20T01:49:11ZengMDPI AGSensors1424-82202025-04-01259267110.3390/s25092671VariGAN: Enhancing Image Style Transfer via UNet Generator, Depthwise Discriminator, and LPIPS Loss in Adversarial Learning FrameworkDawei Guan0Xinping Lin1Haoyi Zhang2Hang Zhou3School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, ChinaImage style transfer is a challenging task that has gained significant attention in recent years due to its growing complexity. Training is typically performed using paradigms offered by GAN-based image style transfer networks. Cycle-based training methods provide an approach for handling unpaired data. Nevertheless, achieving high transfer quality remains a challenge with these methods due to the simplicity of the employed network. The purpose of this research is to present <i>VariGAN</i>, a novel approach that incorporates three additional strategies to optimize GAN-based image style transfer: (1) Improving the quality of transferred images by utilizing an effective UNet generator network in conjunction with a context-related feature extraction module. (2) Optimizing the training process while reducing dependency on the generator through the use of a depthwise discriminator. (3) Introducing LPIPS loss to further refine the loss function and enhance the overall generation quality of the framework. Through a series of experiments, we demonstrate that the <i>VariGAN</i> backbone exhibits superior performance across diverse content and style domains. <i>VariGAN</i> improved class IoU by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>236</mn><mo>%</mo></mrow></semantics></math></inline-formula> and participant identification by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>195</mn><mo>%</mo></mrow></semantics></math></inline-formula> compared to <i>CycleGAN</i>.https://www.mdpi.com/1424-8220/25/9/2671style transferGANLPIPSUNetResNetimage segmentation
spellingShingle Dawei Guan
Xinping Lin
Haoyi Zhang
Hang Zhou
VariGAN: Enhancing Image Style Transfer via UNet Generator, Depthwise Discriminator, and LPIPS Loss in Adversarial Learning Framework
Sensors
style transfer
GAN
LPIPS
UNet
ResNet
image segmentation
title VariGAN: Enhancing Image Style Transfer via UNet Generator, Depthwise Discriminator, and LPIPS Loss in Adversarial Learning Framework
title_full VariGAN: Enhancing Image Style Transfer via UNet Generator, Depthwise Discriminator, and LPIPS Loss in Adversarial Learning Framework
title_fullStr VariGAN: Enhancing Image Style Transfer via UNet Generator, Depthwise Discriminator, and LPIPS Loss in Adversarial Learning Framework
title_full_unstemmed VariGAN: Enhancing Image Style Transfer via UNet Generator, Depthwise Discriminator, and LPIPS Loss in Adversarial Learning Framework
title_short VariGAN: Enhancing Image Style Transfer via UNet Generator, Depthwise Discriminator, and LPIPS Loss in Adversarial Learning Framework
title_sort varigan enhancing image style transfer via unet generator depthwise discriminator and lpips loss in adversarial learning framework
topic style transfer
GAN
LPIPS
UNet
ResNet
image segmentation
url https://www.mdpi.com/1424-8220/25/9/2671
work_keys_str_mv AT daweiguan variganenhancingimagestyletransferviaunetgeneratordepthwisediscriminatorandlpipslossinadversariallearningframework
AT xinpinglin variganenhancingimagestyletransferviaunetgeneratordepthwisediscriminatorandlpipslossinadversariallearningframework
AT haoyizhang variganenhancingimagestyletransferviaunetgeneratordepthwisediscriminatorandlpipslossinadversariallearningframework
AT hangzhou variganenhancingimagestyletransferviaunetgeneratordepthwisediscriminatorandlpipslossinadversariallearningframework