Text Pared into Scene Graph for Diverse Image Generation

Yonghua Zhu, Jieyu Huang, Ning Ge, Yunwen Zhu, Binghui Zheng, Wenjun Zhang
{"title":"Text Pared into Scene Graph for Diverse Image Generation","authors":"Yonghua Zhu, Jieyu Huang, Ning Ge, Yunwen Zhu, Binghui Zheng, Wenjun Zhang","doi":"10.1145/3487075.3487158","DOIUrl":null,"url":null,"abstract":"Although significant recent advances in condition generative model have shown remarkable improvements for controlled image generation, the image generation for multiple complex objects is still a challenge. To address the challenge, we propose a module of text description parsed into scene graph, which can generate reasonable scene layout to ensure the generated image and object realistic. Our proposed method enhances the interaction between objects and global semantics by concatenates each object embedding with text embedding To preserve the local image semantics, the Spatially-adaptive normalization(SPADE) layer is added into the generator of our model. We validate our method on Visual Genome and COCO-Stuff, where qualitative results and ablation study demonstrate the ability of our model in generating images with multiple objects and complex relationships.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3487075.3487158","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Although significant recent advances in condition generative model have shown remarkable improvements for controlled image generation, the image generation for multiple complex objects is still a challenge. To address the challenge, we propose a module of text description parsed into scene graph, which can generate reasonable scene layout to ensure the generated image and object realistic. Our proposed method enhances the interaction between objects and global semantics by concatenates each object embedding with text embedding To preserve the local image semantics, the Spatially-adaptive normalization(SPADE) layer is added into the generator of our model. We validate our method on Visual Genome and COCO-Stuff, where qualitative results and ablation study demonstrate the ability of our model in generating images with multiple objects and complex relationships.
文本分割成场景图用于不同图像的生成
尽管近年来条件生成模型在受控图像生成方面取得了显著进展,但多复杂对象的图像生成仍然是一个挑战。为了解决这一问题,我们提出了一个将文本描述解析为场景图的模块,该模块可以生成合理的场景布局,以保证生成的图像和物体的真实感。我们提出的方法通过将每个对象嵌入与文本嵌入相连接来增强对象与全局语义之间的交互。为了保持局部图像语义,我们在模型的生成器中添加了空间自适应归一化(spatial -adaptive normalization, SPADE)层。我们在Visual Genome和COCO-Stuff上验证了我们的方法,其中定性结果和烧蚀研究证明了我们的模型在生成具有多个对象和复杂关系的图像方面的能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信