FitDiT applies a customized Diffusion Transformer to image-based virtual try-on, adding a garment feature evolution stage, a frequency-domain loss, and a relaxed mask strategy to improve texture and size fidelity.
Reproducible scal- ing laws for contrastive language-image learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on
FitDiT applies a customized Diffusion Transformer to image-based virtual try-on, adding a garment feature evolution stage, a frequency-domain loss, and a relaxed mask strategy to improve texture and size fidelity.