EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A VGG19-based Image Style Transfer Method That Integrates Improved UNet Semantic Segmentation With a Dual-Encoder Architecture

Fei Pan, Yuyan Wu, Yu Chen

Journal of Design Intelligence · 21.07.2026 · 1 (3) · 51-60

DOI: 10.64509/jdi.13.102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Design Intelligence, online erschienen am 21.07.2026. Verfasst von Fei Pan und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the common issues of image artifacts, background contamination, and loss of fine texture details in clothing design image translation using the existing VGG19 software, this paper proposes an improved VGG19 network method that incorporates a dual-encoder architecture, a hybrid-domain loss function, and a high-precision semantic mask generated by an improved UNet. In this method, power mean pooling and the SimAM attention mechanism are introduced to the VGG19 network, and two independent encoders are employed to extract and couple the structural features of the clothing and the style features of the image, respectively. The improvements include: 1) using a hybrid-domain loss function with wavelet-domain adjustments to constrain clothing structure and image style; 2) applying a high-precision spatial-domain mask—generated by an improved UNet semantic segmentation network—to completely purify the image background; and 3) employing a total variation loss function to achieve smooth transitions between image contents. Experimental results demonstrate that, compared to the traditional VGG19 network method, the proposed method improves the PSNR and SSIM metrics by 19.5% and 30.9%, respectively, while achieving a remarkable 36.8% reduction in the LPIPS metric, thereby facilitating the application of the VGG19 network method in clothing image style transfer.

Zitieren

APA

Pan, F., Wu, Y., & Chen, Y. (2026). A VGG19-based Image Style Transfer Method That Integrates Improved UNet Semantic Segmentation With a Dual-Encoder Architecture. Journal of Design Intelligence, 1(3), 51-60. https://doi.org/10.64509/jdi.13.102

Vancouver

Pan F, Wu Y, Chen Y. A VGG19-based Image Style Transfer Method That Integrates Improved UNet Semantic Segmentation With a Dual-Encoder Architecture. Journal of Design Intelligence. 2026;1(3):51-60. doi:10.64509/jdi.13.102

BibTeX
@article{Pan2026,
  author = {Pan, Fei and Wu, Yuyan and Chen, Yu},
  title = {A VGG19-based Image Style Transfer Method That Integrates Improved UNet Semantic Segmentation With a Dual-Encoder Architecture},
  journal = {Journal of Design Intelligence},
  year = {2026},
  volume = {1},
  number = {3},
  pages = {51--60},
  doi = {10.64509/jdi.13.102}
}
Kostenlos starten →