You're currently viewing an old version of this dataset. To see the current version, click here.

VITON-HD

Virtual try-on focuses on adjusting the given clothes to fit a specific person seamlessly while avoiding any distortion of the patterns and textures of the garment. The clothing identity uncontrollability and training inefficiency of existing diffusion-based methods, which struggle to maintain the identity even with full parameter training, are significant limitations that hinder the widespread applications.

Data and Resources

Cite this as

Seunghwan Choi, Sunghyun Park, Minsoo Lee, Jaegul Choo (2024). Dataset: VITON-HD. https://doi.org/10.57702/f02ny1qd

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2407.10625
Citation
  • https://doi.org/10.48550/arXiv.2303.13756
  • https://doi.org/10.48550/arXiv.2404.17364
  • https://doi.org/10.48550/arXiv.2404.00878
Author Seunghwan Choi
More Authors
Sunghyun Park
Minsoo Lee
Jaegul Choo
Homepage https://arxiv.org/abs/2106.09567