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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ackermann, Jan, Nakayama, Kiyohiro, Yang, Guandao, Wu, Tong, Wetzstein, Gordon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908428001083392
author Ackermann, Jan
Nakayama, Kiyohiro
Yang, Guandao
Wu, Tong
Wetzstein, Gordon
author_facet Ackermann, Jan
Nakayama, Kiyohiro
Yang, Guandao
Wu, Tong
Wetzstein, Gordon
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05210
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Vision-Language-Garment Models for Web Knowledge Garment Understanding and Generation
Ackermann, Jan
Nakayama, Kiyohiro
Yang, Guandao
Wu, Tong
Wetzstein, Gordon
Computer Vision and Pattern Recognition
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.
title Towards Vision-Language-Garment Models for Web Knowledge Garment Understanding and Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.05210