A two-part method, synthetic garment-pair data augmentation plus an error-aware Schrödinger bridge refiner, improves virtual try-on quality on VITON-HD and DressCode-Upper.
Diffusion posterior sampling for general noisy inverse problems
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
-
Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling
A two-part method, synthetic garment-pair data augmentation plus an error-aware Schrödinger bridge refiner, improves virtual try-on quality on VITON-HD and DressCode-Upper.