Multi-Discriminator Generative Adversarial Network for High Resolution Gray-Scale Satellite Image Colorization | |
Li FM(李非墨)![]() ![]() ![]() | |
2018-11 | |
会议名称 | IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium |
会议日期 | 22-27 July 2018 |
会议地点 | Valencia, Spain |
摘要 | Automatic colorization for grayscale satellite images can help with eliminating lighting differences between multi-spectral captures, and provides strong prior information for ground type classification and object detection. In this paper, we introduced a novel generative adversarial network with multiple discriminators for colorizing gray-scale satellite images with pseudo-natural appearances. Although being powerful, deep generative model in its common form with a single discriminator could be unstable for achieving spatial consistency on local textured regions, especially highly textured ones. To address this issue, the generator in our proposed structure produces a group of colored outputs from feature maps at different scale levels of the network, each being supervised by an independent discriminator to fit the original colored training input in discrete Lab color space. The final colored output is a cascaded ensemble of these preceding by-products via summation, thus the fitting errors are reduced by a geometric series form. Quantitative and qualitative comparisons with the sole-discriminator version have been performed on highresolution satellite images in experiments, where significant reductions in prediction errors have been observed. |
关键词 | pseudo-natural colorization gray-scale satellite images generative adversarial network multiple discriminators |
学科领域 | 模式识别 |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 10.1109/IGARSS.2018.8517930 |
URL | 查看原文 |
收录类别 | EI |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/26077 |
专题 | 综合信息系统研究中心 |
通讯作者 | Li FM(李非墨); Ma L(马雷) |
作者单位 | 中国科学院自动化研究所 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li FM,Ma L,Cai J. Multi-Discriminator Generative Adversarial Network for High Resolution Gray-Scale Satellite Image Colorization[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 | ||
li2018.pdf(1079KB) | 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