ChatGarment: Garment Estimation, Generation and Editing via Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bian, Siyuan, Xu, Chenghao, Xiu, Yuliang, Grigorev, Artur, Liu, Zhen, Lu, Cewu, Black, Michael J., Feng, Yao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908298037428224
author Bian, Siyuan
Xu, Chenghao
Xiu, Yuliang
Grigorev, Artur
Liu, Zhen
Lu, Cewu
Black, Michael J.
Feng, Yao
author_facet Bian, Siyuan
Xu, Chenghao
Xiu, Yuliang
Grigorev, Artur
Liu, Zhen
Lu, Cewu
Black, Michael J.
Feng, Yao
contents We introduce ChatGarment, a novel approach that leverages large vision-language models (VLMs) to automate the estimation, generation, and editing of 3D garments from images or text descriptions. Unlike previous methods that struggle in real-world scenarios or lack interactive editing capabilities, ChatGarment can estimate sewing patterns from in-the-wild images or sketches, generate them from text descriptions, and edit garments based on user instructions, all within an interactive dialogue. These sewing patterns can then be draped on a 3D body and animated. This is achieved by finetuning a VLM to directly generate a JSON file that includes both textual descriptions of garment types and styles, as well as continuous numerical attributes. This JSON file is then used to create sewing patterns through a programming parametric model. To support this, we refine the existing programming model, GarmentCode, by expanding its garment type coverage and simplifying its structure for efficient VLM fine-tuning. Additionally, we construct a large-scale dataset of image-to-sewing-pattern and text-to-sewing-pattern pairs through an automated data pipeline. Extensive evaluations demonstrate ChatGarment's ability to accurately reconstruct, generate, and edit garments from multimodal inputs, highlighting its potential to simplify workflows in fashion and gaming applications. Code and data are available at https://chatgarment.github.io/ .
format Preprint
id arxiv_https___arxiv_org_abs_2412_17811
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
Bian, Siyuan
Xu, Chenghao
Xiu, Yuliang
Grigorev, Artur
Liu, Zhen
Lu, Cewu
Black, Michael J.
Feng, Yao
Computer Vision and Pattern Recognition
We introduce ChatGarment, a novel approach that leverages large vision-language models (VLMs) to automate the estimation, generation, and editing of 3D garments from images or text descriptions. Unlike previous methods that struggle in real-world scenarios or lack interactive editing capabilities, ChatGarment can estimate sewing patterns from in-the-wild images or sketches, generate them from text descriptions, and edit garments based on user instructions, all within an interactive dialogue. These sewing patterns can then be draped on a 3D body and animated. This is achieved by finetuning a VLM to directly generate a JSON file that includes both textual descriptions of garment types and styles, as well as continuous numerical attributes. This JSON file is then used to create sewing patterns through a programming parametric model. To support this, we refine the existing programming model, GarmentCode, by expanding its garment type coverage and simplifying its structure for efficient VLM fine-tuning. Additionally, we construct a large-scale dataset of image-to-sewing-pattern and text-to-sewing-pattern pairs through an automated data pipeline. Extensive evaluations demonstrate ChatGarment's ability to accurately reconstruct, generate, and edit garments from multimodal inputs, highlighting its potential to simplify workflows in fashion and gaming applications. Code and data are available at https://chatgarment.github.io/ .
title ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.17811