Considering the success of generative adversarial networks (GANs) for image-to-image translation, researchers have attempted to translate remote sensing images (RSIs) to maps (rs2map) through GAN for cartography. However, these studies involved limited scales, which hinders multi-scale map creation. By extending their method, multi-scale RSIs can be trivially translated to multi-scale maps (multi-scale rs2map translation) through scale-wise rs2map models trained for certain scales (parallel strategy). However, this strategy has two theoretical limitations. First, inconsistency between various spatial resolutions of multi-scale RSIs and object generalization on multi-scale maps (RS-m inconsistency) increasingly complicate the extraction of geographical information from RSIs for rs2map models with decreasing scale. Second, as rs2map translation is cross-domain, generators incur high computation costs to transform the RSI pixel distribution to that on maps. Thus, we designed a series strategy of generators for multi-scale rs2map translation to address these limitations. In this strategy, high-resolution RSIs are inputted to an rs2map model to output large-scale maps, which are translated to multi-scale maps through series multi-scale map translation models. The series strategy avoids RS-m inconsistency as inputs are high-resolution large-scale RSIs, and reduces the distribution gap in multi-scale map generation through similar pixel distributions among multi-scale maps. Our experimental results showed better quality multi-scale map generation with the series strategy, as shown by average increases of 11.69%, 53.78%, 55.42%, and 72.34% in the structural similarity index, edge structural similarity index, intersection over union (road), and intersection over union (water) for data from Mexico City and Tokyo at zoom level 17-13.


翻译:考虑到图像到图像翻译的基因对抗网络(GANs)的成功,研究人员试图通过GAN将遥感图像(RSI)转换成地图(RS2map),然而,这些研究涉及规模有限,妨碍了多尺度地图的创建。通过扩大方法,多尺度的RSI可以微不足道地被转换成多尺度的地图(多尺度的RS2map翻译),通过为某些比例(parallel 战略)培训的SBY RS2map模型。然而,这一战略有两个理论限制。首先,多尺度的RSI和多尺度地图(RS2mapmmm)的空间分辨率分辨率分辨率和目标(rs2mapm)之间的不一致。首先,多尺度的RSI和多尺度的实验性(RSI)的空间分辨率和实验性(RSMS-S-S-S-S-Seral-Servicalalalal-imation)的分布,通过高尺度的地图显示比例比例比例尺的分布。因此,高尺度的RSI-sal-imal-imal-imalalalalalal-imalal-imal-imal-imal-imal-imal-imal-al-al-al-al-al-masmal-al-al-immal-al-masal-masal-lax-lax-masal-al-max-maxal-al-al-al-al-masmal-masmal-al-mod-mo-mo-mod-mod-lation-lation-mod-mod-mod-maxal-mod-maxal-mod-mod-max-mod-mod-mod-mod-mod-mod-mod-mod-moal-mod-mod-mod-mod-mod-moal-modal-moal-modal-mod-modal-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-moal-mod-mo

0
下载
关闭预览

相关内容

生成对抗网络 (Generative Adversarial Network, GAN) 是一类神经网络,通过轮流训练判别器 (Discriminator) 和生成器 (Generator),令其相互对抗,来从复杂概率分布中采样,例如生成图片、文字、语音等。GAN 最初由 Ian Goodfellow 提出,原论文见 Generative Adversarial Networks

知识荟萃

精品入门和进阶教程、论文和代码整理等

更多

查看相关VIP内容、论文、资讯等
专知会员服务
109+阅读 · 2020年3月12日
[综述]深度学习下的场景文本检测与识别
专知会员服务
77+阅读 · 2019年10月10日
【SIGGRAPH2019】TensorFlow 2.0深度学习计算机图形学应用
专知会员服务
39+阅读 · 2019年10月9日
GAN新书《生成式深度学习》,Generative Deep Learning,379页pdf
专知会员服务
201+阅读 · 2019年9月30日
【泡泡汇总】CVPR2019 SLAM Paperlist
泡泡机器人SLAM
14+阅读 · 2019年6月12日
Transferring Knowledge across Learning Processes
CreateAMind
27+阅读 · 2019年5月18日
强化学习的Unsupervised Meta-Learning
CreateAMind
17+阅读 · 2019年1月7日
Unsupervised Learning via Meta-Learning
CreateAMind
41+阅读 · 2019年1月3日
计算机视觉近一年进展综述
机器学习研究会
9+阅读 · 2017年11月25日
gan生成图像at 1024² 的 代码 论文
CreateAMind
4+阅读 · 2017年10月31日
Auto-Encoding GAN
CreateAMind
7+阅读 · 2017年8月4日
Slimmable Generative Adversarial Networks
Arxiv
3+阅读 · 2020年12月10日
Generative Adversarial Networks: A Survey and Taxonomy
Arxiv
8+阅读 · 2018年5月21日
VIP会员
Top
微信扫码咨询专知VIP会员