Knowledge Commons of Institute of Automation,CAS
Semantic Image Synthesis via Conditional Cycle-Generative Adversarial Networks | |
Xiyan Liu1,2; Gaofeng Meng1,2; Shiming Xiang1,2; Chunhong Pan1 | |
2018 | |
会议名称 | 24th International Conference on Pattern Recognition (ICPR) |
会议日期 | August 20-24, 2018 |
会议地点 | Beijing, China |
摘要 | Traditional approaches for semantic image synthesis mainly focus on text descriptions while ignoring the related structures and attributes in the original images. Therefore, some critical information, e.g., the style, backgrounds, objects shapes and pose, is missed in the generated images. In this paper, we propose a novel framework called Conditional Cycle-Generative Adversarial Network (CCGAN) to address this issue. Our model can generate photo-realistic images conditioned on the given text descriptions, while maintaining the attributes of the original images. The framework mainly consists of two coupled conditional adversarial networks, which are able to learn a desirable image mapping that can keep the structures and attributes in the images. We introduce a conditional cycle consistency loss to prevent the contradiction between two generators. This loss allows the generated images to retain most of the features of the original image, so as to improve the stability of network training. Moreover, benefiting from the mechanism of circular training, the proposed networks can learn the semantic information of the text much accurately. Experiments on Caltech-UCSD Bird dataset and Oxford-102 flower dataset demonstrate that the proposed method significantly outperforms the existing methods in terms of image details reconstruction and semantic information expression. |
关键词 | Image synthesis Text-to-image Generative adversarial networks |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/46643 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Gaofeng Meng |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Xiyan Liu,Gaofeng Meng,Shiming Xiang,et al. Semantic Image Synthesis via Conditional Cycle-Generative Adversarial Networks[C],2018. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Semantic_Image_Synth(4929KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论