An Efficient Information-Reinforced Lidar Deep Completion Network without RGB Guided

doi:10.3390/rs14194689

CIOMP OpenIR

	An Efficient Information-Reinforced Lidar Deep Completion Network without RGB Guided
	M. Wei; M. Zhu; Y. Y. Zhang; J. Q. Sun and J. R. Wang
	2022
发表期刊	Remote Sensing
卷号	14 期号:19 页码:17
摘要	Due to the sparsity of point clouds obtained by LIDAR, the depth information is usually not complete and dense. The depth completion task is to recover dense depth information from sparse depth information. However, most of the current deep completion networks use RGB images as guidance, which are more like a processing method of information fusion. They are not valid when there is only sparse depth data and no other color information. Therefore, this paper proposes an information-reinforced completion network for a single sparse depth input. We use a multi-resolution dense progressive fusion structure to maximize the multi-scale information and optimize the global situation by point folding. At the same time, we re-aggregate the confidence and impose another depth constraint on the pixel depth to make the depth estimation closer to the ground trues. Our experimental results on KITTI and NYU Depth v2 datasets show that the proposed network achieves better results than other unguided deep completion methods. And it is excellent in both accuracy and real-time performance.
DOI	10.3390/rs14194689
URL	查看原文
收录类别	sci ; ei
语种	英语
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/66603
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	M. Wei,M. Zhu,Y. Y. Zhang,et al. An Efficient Information-Reinforced Lidar Deep Completion Network without RGB Guided[J]. Remote Sensing,2022,14(19):17.
APA	M. Wei,M. Zhu,Y. Y. Zhang,&J. Q. Sun and J. R. Wang.(2022).An Efficient Information-Reinforced Lidar Deep Completion Network without RGB Guided.Remote Sensing,14(19),17.
MLA	M. Wei,et al."An Efficient Information-Reinforced Lidar Deep Completion Network without RGB Guided".Remote Sensing 14.19(2022):17.

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
An Efficient Informa（3903KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载