Development of a Deep Learning-based Program for User’s Virtual Try-on Images and Short Forms Generation in Fashion 


Vol. 62,  No. 2, pp. 91-100, Apr.  2025
10.12772/TSE.2025.62.091


PDF
  Abstract

The study presents the development of an immersive virtual fitting program leveraging deepfake technology and its extension to video formats. Traditional online shopping environments have been limited by challenges such as the inability to try on clothing, lack of realism, and restricted selection of apparel, thereby constraining the consumer experience. This research integrates advanced deep learning technologies, including StableVITON, DeepFaceLab, and MusePose, to seamlessly synthesize consumer facial images with model images and adapt selected garments appropriately. Furthermore, motion synthesis was implemented to provide virtual fitting results in video format, enabling a more realistic and natural user experience. The results demonstrate that the program achieves high-quality synthesis not only for apparel from specific retailers but also for garments from diverse sources, offering a highly realistic fitting experience. Future developments will focus on optimizing code efficiency and expanding into 3D domains to deliver faster and more precise virtual fitting services.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

박창규, 황준형, 문형민, 최승아, 고준석, 박창규, "Development of a Deep Learning-based Program for User’s Virtual Try-on Images and Short Forms Generation in Fashion," Textile Science and Engineering, vol. 62, no. 2, pp. 91-100, 2025. DOI: 10.12772/TSE.2025.62.091.

[ACM Style]

박창규, 황준형, 문형민, 최승아, 고준석, and 박창규. 2025. Development of a Deep Learning-based Program for User’s Virtual Try-on Images and Short Forms Generation in Fashion. Textile Science and Engineering, 62, 2, (2025), 91-100. DOI: 10.12772/TSE.2025.62.091.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

pISSN : 1225 - 1089
eISSN : 2288 - 6419

한국연구재단 우수등재학술지 유지 (2022년)