.png){kind=icon}
Return
Diffusion model-based size variable virtual try-on technology and evaluation method
.png){kind=icon}
PRE
AI
DOI：10.1016/j.cag.2025.104448.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• SV-VTON enables multi-size virtual try-on with tight, fitted, and loose styles. • A two-stage mask generation strategy improves accuracy for size variations. • Edge Attention and U2-Net refine garment-human boundaries for realistic fitting. • A novel metric quantitatively evaluates size variation across four key dimensions. • The framework supports practical applications in e-commerce and virtual try-on.
Journal
C
IF:
0
Papers:
119
Citations:
0
Organization
Cited Papers
No cited papers available