Generative AI in Fashion: Overview

计算机科学 生成语法 人工智能 生成模型 自然语言处理
作者
Wei-Pei Shi,Wai Keung Wong,Xingxing Zou
出处
期刊:ACM Transactions on Intelligent Systems and Technology [Association for Computing Machinery]
被引量:44
标识
DOI:10.1145/3718098
摘要

Generative Artificial Intelligence (GenAI) has recently gained immense popularity by offering various applications for generating high-quality and aesthetically pleasing content of image, 3D, and video data format. The innovative GenAI solutions have shifted paradigms across various design-related industries, particularly fashion. In this paper, we explore the incorporation of GenAI into fashion-related tasks and applications. Our examination encompasses a thorough review of more than 470 research papers and an in-depth analysis of over 300 applications, focusing on their contributions to the field. These contributions are identified as 13 tasks within four categories: multi-modal fashion understanding, and fashion synthesis of image, 3D, and dynamic (video and animatable 3D) formats We delve into these methods, recognizing their potential to propel future endeavours toward achieving state-of-the-art (SOTA) performance. Furthermore, we present a comprehensive overview of 53 publicly available datasets suitable for training and benchmarking fashion-centric models, accompanied by the relevant evaluation metrics. Finally, we review real-world applications, unveiling existing challenges and future directions. With comprehensive investigation and in-depth analysis, this paper is targeted to serve as a useful resource for understanding the current landscape of GenAI in fashion, paving the way for future innovations in this dynamic field. Papers discussed in this paper, along with public code and datasets links are available at: https://github.com/wendashi/Cool-GenAI-Fashion-Papers/ .
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Wei的应助被同心源采纳,获得10
刚刚
希望天下0贩的0的应助被lll采纳,获得10
刚刚
gengar发布了新的文献求助10
1秒前
青芷完成签到,获得积分10
2秒前
2秒前
zhangyupei的应助被弗洛伊德采纳,获得10
2秒前
万能图书馆的应助被一木采纳,获得10
3秒前
DYF发布了新的文献求助10
3秒前
4秒前
deletelzr完成签到,获得积分10
4秒前
牧百川发布了新的文献求助10
4秒前
周程朋完成签到,获得积分10
5秒前
5秒前
洁洁发布了新的文献求助10
5秒前
一顿吃六个馒头完成签到,获得积分10
5秒前
9秒前
10秒前
12秒前
青松完成签到,获得积分10
12秒前
共享精神的应助被缓慢念波采纳,获得10
14秒前
14秒前
美好明辉发布了新的文献求助10
14秒前
烫水一壶完成签到,获得积分10
14秒前
15秒前
Ying发布了新的文献求助10
15秒前
Akim的应助被darkegg采纳,获得10
15秒前
牧百川发布了新的文献求助10
16秒前
沉沉叠叠发布了新的文献求助10
16秒前
Jun的应助被晴天采纳,获得10
16秒前
gengar完成签到,获得积分20
17秒前
17秒前
酷波er的应助被禾十采纳,获得10
17秒前
冷艳的河马完成签到,获得积分10
19秒前
20秒前
20秒前
SPP完成签到 ,获得积分10
21秒前
21秒前
Dispute完成签到,获得积分10
21秒前
樊家圣完成签到 ,获得积分10
21秒前
小呆鹿完成签到,获得积分10
22秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183621
求助须知:如何正确求助?哪些是违规求助? 9572918
关于积分的说明 21828010
捐赠科研通 7780809
什么是DOI,文献DOI怎么找? 3434031
关于科研通互助平台的介绍 2558243
邀请新用户注册赠送积分活动 2480496