A Comprehensive Survey of Image Generation Models Based on Deep Learning

Q1 Decision Sciences Annals of Data Science Pub Date : 2024-06-20 DOI:10.1007/s40745-024-00544-1
Jun Li, Chenyang Zhang, Wei Zhu, Yawei Ren
{"title":"A Comprehensive Survey of Image Generation Models Based on Deep Learning","authors":"Jun Li,&nbsp;Chenyang Zhang,&nbsp;Wei Zhu,&nbsp;Yawei Ren","doi":"10.1007/s40745-024-00544-1","DOIUrl":null,"url":null,"abstract":"<div><p>In recent years, generative artificial intelligence has been developing rapidly. In the image domain, image generation models based on deep learning have made remarkable achievements. Early frameworks for image generation models were dominated by generative adversarial networks (GANs) and variational autoencoders (VAEs). Nowadays, large-scale generative models based on diffusion models have become mainstream, and the quality of their generated images is significantly improved. We will review the research and development of image generation models and delve into the significant progress made in the field in recent years. Initially, we revisit the development of traditional image generation models like GANs and VAEs, emphasizing their contributions and challenges. We also introduce diffusion models, which have received much attention in the field of image generation due to their unique generative process and excellent generative performance. Subsequently, we emphasized the large vision models with SAM as the focal point. We also pay special attention to large-scale generative models like Stable Diffusion, which have demonstrated unprecedented capabilities in high-quality image generation tasks. Additionally, we explore target models and respective fine-tuning methods for domain-oriented image generation tasks, predicts future directions in image generation, and proposes potential research focuses and challenges.</p></div>","PeriodicalId":36280,"journal":{"name":"Annals of Data Science","volume":"12 1","pages":"141 - 170"},"PeriodicalIF":0.0000,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Data Science","FirstCategoryId":"1085","ListUrlMain":"https://link.springer.com/article/10.1007/s40745-024-00544-1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Decision Sciences","Score":null,"Total":0}
引用次数: 0

Abstract

In recent years, generative artificial intelligence has been developing rapidly. In the image domain, image generation models based on deep learning have made remarkable achievements. Early frameworks for image generation models were dominated by generative adversarial networks (GANs) and variational autoencoders (VAEs). Nowadays, large-scale generative models based on diffusion models have become mainstream, and the quality of their generated images is significantly improved. We will review the research and development of image generation models and delve into the significant progress made in the field in recent years. Initially, we revisit the development of traditional image generation models like GANs and VAEs, emphasizing their contributions and challenges. We also introduce diffusion models, which have received much attention in the field of image generation due to their unique generative process and excellent generative performance. Subsequently, we emphasized the large vision models with SAM as the focal point. We also pay special attention to large-scale generative models like Stable Diffusion, which have demonstrated unprecedented capabilities in high-quality image generation tasks. Additionally, we explore target models and respective fine-tuning methods for domain-oriented image generation tasks, predicts future directions in image generation, and proposes potential research focuses and challenges.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
求助全文
约1分钟内获得全文 去求助
来源期刊
Annals of Data Science
Annals of Data Science Decision Sciences-Statistics, Probability and Uncertainty
CiteScore
6.50
自引率
0.00%
发文量
93
期刊介绍: Annals of Data Science (ADS) publishes cutting-edge research findings, experimental results and case studies of data science. Although Data Science is regarded as an interdisciplinary field of using mathematics, statistics, databases, data mining, high-performance computing, knowledge management and virtualization to discover knowledge from Big Data, it should have its own scientific contents, such as axioms, laws and rules, which are fundamentally important for experts in different fields to explore their own interests from Big Data. ADS encourages contributors to address such challenging problems at this exchange platform. At present, how to discover knowledge from heterogeneous data under Big Data environment needs to be addressed.     ADS is a series of volumes edited by either the editorial office or guest editors. Guest editors will be responsible for call-for-papers and the review process for high-quality contributions in their volumes.
期刊最新文献
Identifying the Intents Behind Website Visits by Employing Unsupervised Machine Learning Models A Novel Finite Mixture Model Based on the Generalized t Distributions with Two-Sided Censored Data Gated Graph Attention-based Crossover Snake (GGA-CS) Algorithm for Hyperspectral Image Classification Kernel-free Reduced Quadratic Surface Support Vector Machine with 0-1 Loss Function and L\(_p\)-norm Regularization Non-negative Sparse Matrix Factorization for Soft Clustering of Territory Risk Analysis
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1