MGT is a unified diffusion model that reconstructs clean garment images from photos of dressed people for three garment classes, and it improves person-to-person virtual try-on when paired with OOTDiffusion.
Vis- conet: Bridging and harmonizing visual and textual condi- tioning for controlnet
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MGT: Extending Virtual Try-Off to Multi-Garment Scenarios
MGT is a unified diffusion model that reconstructs clean garment images from photos of dressed people for three garment classes, and it improves person-to-person virtual try-on when paired with OOTDiffusion.