English

Towards Vision-Language-Garment Models for Web Knowledge Garment Understanding and Generation

Computer Vision and Pattern Recognition 2025-07-01 v2

Abstract

Multimodal foundation models have demonstrated strong generalization, yet their ability to transfer knowledge to specialized domains such as garment generation remains underexplored. We introduce VLG, a vision-language-garment model that synthesizes garments from textual descriptions and visual imagery. Our experiments assess VLG's zero-shot generalization, investigating its ability to transfer web-scale reasoning to unseen garment styles and prompts. Preliminary results indicate promising transfer capabilities, highlighting the potential for multimodal foundation models to adapt effectively to specialized domains like fashion design.

Keywords

Cite

@article{arxiv.2506.05210,
  title  = {Towards Vision-Language-Garment Models for Web Knowledge Garment Understanding and Generation},
  author = {Jan Ackermann and Kiyohiro Nakayama and Guandao Yang and Tong Wu and Gordon Wetzstein},
  journal= {arXiv preprint arXiv:2506.05210},
  year   = {2025}
}

Comments

Presented at MMFM CVPRW'25, Project Page: https://www.computationalimaging.org/publications/vision-language-garment-models/

R2 v1 2026-07-01T03:01:52.665Z