A fine-tuned vision-language model can predict sewing patterns from unseen garment images and prompts better than non-pretrained baselines, but the result rests on a self-generated evaluation set.
Improving diffusion models for au- thentic virtual try-on in the wild
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
-
Towards Vision-Language-Garment Models for Web Knowledge Garment Understanding and Generation
A fine-tuned vision-language model can predict sewing patterns from unseen garment images and prompts better than non-pretrained baselines, but the result rests on a self-generated evaluation set.