EUVIMEDEUVIMED entdecken
Crossref

VTON-MP: Multi-Pose Virtual Try-On via Appearance Flow and Feature Filtering

Feng Yu, Ailing Hua, Chenghu Du, Minghua Jiang, Xiong Wei, Tao Peng, Lijun Xu, Xinrong Hu

IEEE Transactions on Consumer Electronics · 2023-11 · 69 (4) · 1101-1113

DOI: 10.1109/tce.2023.3306206 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2023-11. Verfasst von Feng Yu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: Hubei Key Research and Development Program, Wuhan Applied Basic Frontier Research Project, MIIT’s AI Industry Innovation Task Unveils Flagship Projects.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-pose virtual try-on has become a research focus for online clothes shopping due to the fixed-pose virtual try-on methods that cannot provide a different pose try-on effect. The challenge of multi-pose virtual try-on is that the detailed information of a generated image is difficult to obtain in the pose transformation and garment distortion. To solve the issue, we propose a multi-pose virtual try-on method via appearance flow and feature filtering (VTON-MP). First, a segmentation generation network of 2D keypoints about the target pose is used to predict the body semantic distribution of the target pose. Second, the desired garment is distorted to correspond to the body posture using the appearance flow figure alignment network (AFFAN). Third, latent useless feature weights are restrained using a filtering-enhancement block (FEB), and effective appearance feature weights are enhanced. Finally, the spatial relationship of body parts in the resulting image is further optimized using spatially-adaptive instance normalization (SAIN). Compared to state-of-the-art methods of subjective and objective experiments on the MPV dataset, the proposed VTON-MP achieves the best performance in terms of SSIM, PSNR and FID. The experimental results demonstrate that the proposed algorithm can better retain image details (head, hands, arms, and trousers).

Förderung

  • Hubei Key Research and Development Program
  • Wuhan Applied Basic Frontier Research Project
  • MIIT’s AI Industry Innovation Task Unveils Flagship Projects

Zitieren

APA

Yu, F., Hua, A., Du, C., Jiang, M., Wei, X., Peng, T., Xu, L., & Hu, X. (2023). VTON-MP: Multi-Pose Virtual Try-On via Appearance Flow and Feature Filtering. IEEE Transactions on Consumer Electronics, 69(4), 1101-1113. https://doi.org/10.1109/tce.2023.3306206

Vancouver

Yu F, Hua A, Du C, Jiang M, Wei X, Peng T, et al. VTON-MP: Multi-Pose Virtual Try-On via Appearance Flow and Feature Filtering. IEEE Transactions on Consumer Electronics. 2023;69(4):1101-1113. doi:10.1109/tce.2023.3306206

BibTeX
@article{Yu2023,
  author = {Yu, Feng and Hua, Ailing and Du, Chenghu and Jiang, Minghua and Wei, Xiong and Peng, Tao and Xu, Lijun and Hu, Xinrong},
  title = {VTON-MP: Multi-Pose Virtual Try-On via Appearance Flow and Feature Filtering},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2023},
  volume = {69},
  number = {4},
  pages = {1101--1113},
  doi = {10.1109/tce.2023.3306206}
}
Kostenlos starten →