Lune

CVPR2020顶会

Through Fog High-Resolution Imaging Using Millimeter Wave Radar

Junfeng Guan, Sohrab Madani, Suraj Jog, Saurabh Gupta, Haitham Hassanieh

2020年份
29顶会引用

摘要

Champaign (a) Original Scene (c) Camera in Fog (b) Ground Truth (e) Radar Heatmap in Fog (f) Recovered Image (d) Radar Point Cloud in Fog 3 4 5 6 7 12 16 8 10 14 (m) Figure 1: Millimeter wave radar can image through fog and bad weather. However, specularity, artifacts and low resolution result in poor perceptual quality as shown in Figure (d) and (e) above. To overcome this limitation, this paper leverages a cGAN architecture to recover high resolution images from the low resolution mmWave radar heatmaps. The figure above shows (a) the original scene, (b) ground truth depth map captured with stereo camera and cropped using MaskRCNN (before fog is generated), (c) the scene in fog, (d) the millimeter wave radar point cloud generated in the presence of fog, (e) the corresponding radar heatmap, and (f) the recovered output of our system.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

引用它的顶会 Paper29

问问它们各自怎么用它

它引用的顶会 Paper1

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖