DressCode: Autoregressively Sewing and Generating Garments from Text Guidance

doi:10.1145/3658147

	DressCode: Autoregressively Sewing and Generating Garments from Text Guidance
	He, Kai1,2 ; Yao, Kaixin2,3 ; Zhang, Qixuan1,2 ; Yu, Jingyi2 ; Liu, Lingjie 4; Xu, Lan2
	2024-07-19
发表期刊	ACM TRANSACTIONS ON GRAPHICS (IF:7.8[JCR-2023],9.5[5-Year])
ISSN	0730-0301
EISSN	1557-7368
卷号	43 期号:4
发表状态	已发表
DOI	10.1145/3658147
摘要	Apparel's significant role in human appearance underscores the importance of garment digitalization for digital human creation. Recent advances in 3D content creation are pivotal for digital human creation. Nonetheless, garment generation from text guidance is still nascent. We introduce a text-driven 3D garment generation framework, DressCode, which aims to democratize design for novices and offer immense potential in fashion design, virtual try-on, and digital human creation. We first introduce SewingGPT, a GPT-based architecture integrating cross-attention with text-conditioned embedding to generate sewing patterns with text guidance. We then tailor a pre-trained Stable Diffusion to generate tile-based Physically-based Rendering (PBR) textures for the garments. By leveraging a large language model, our framework generates CG-friendly garments through natural language interaction. It also facilitates pattern completion and texture editing, streamlining the design process through user-friendly interaction. This framework fosters innovation by allowing creators to freely experiment with designs and incorporate unique elements into their work. With comprehensive evaluations and comparisons with other state-of-the-art methods, our method showcases superior quality and alignment with input prompts. User studies further validate our high-quality rendering results, highlighting its practical utility and potential in production settings. Copyright © 2024 held by the owner/author(s).
关键词	Interactive computer graphics Virtual reality 3D content 3d garments Autoregressive modelling Content creation Digital humans Embeddings Fashion design Garment generation Sewing pattern Virtual try-on
URL	查看原文
收录类别	EI ; SCI
语种	英语
资助项目	National Key R&D Program of China[2022YFF0902301] ; NSFC programs["61976138","61977047"] ; STCSM["2015F0203-000-06","2019-01-07-00-01-E00003"]
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:001289270900039
出版者	Association for Computing Machinery
EI入藏号	20243016756649
EI主题词	Textures
EI分类号	723 Computer Software, Data Handling and Applications ; 723.5 Computer Applications
原始文献类型	Journal article (JA)
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/407214
专题	信息科学与技术学院_博士生信息科学与技术学院_PI研究组_虞晶怡组信息科学与技术学院_硕士生信息科学与技术学院_本科生信息科学与技术学院_PI研究组_许岚组
通讯作者	Yu, Jingyi; Liu, Lingjie; Xu, Lan
作者单位	1.Deemos Technology, Shanghai, China; 2.ShanghaiTech University, Shanghai, China; 3.NeuDim, Shanghai, China; 4.University of Pennsylvania, Philadelphia; PA, United States
第一作者单位	上海科技大学
通讯作者单位	上海科技大学
推荐引用方式 GB/T 7714	He, Kai,Yao, Kaixin,Zhang, Qixuan,et al. DressCode: Autoregressively Sewing and Generating Garments from Text Guidance[J]. ACM TRANSACTIONS ON GRAPHICS,2024,43(4).
APA	He, Kai,Yao, Kaixin,Zhang, Qixuan,Yu, Jingyi,Liu, Lingjie,&Xu, Lan.(2024).DressCode: Autoregressively Sewing and Generating Garments from Text Guidance.ACM TRANSACTIONS ON GRAPHICS,43(4).
MLA	He, Kai,et al."DressCode: Autoregressively Sewing and Generating Garments from Text Guidance".ACM TRANSACTIONS ON GRAPHICS 43.4(2024).