Unsupervised deep depth completion with heterogeneous LiDAR and RGB-D camera depth information

In this work, a depth-only completion method designed to enhance perception in light-deprived environments. We achieve this through LidarDepthNet, a novel end-to-end unsupervised learning framework that fuses heterogeneous depth information captured by two distinct depth sensors: LiDAR and RGB-D cam...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Guohua Gou, Han Li, Xuanhao Wang, Hao Zhang, Wei Yang, Haigang Sui
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Elsevier 2025-02-01
coleção:	International Journal of Applied Earth Observations and Geoinformation
Assuntos:	Depth completion Depth-only inputs Heterogeneous depth information Unsupervised deep learning Temporal depth consistency loss Depth measurement confidence
Acesso em linha:	http://www.sciencedirect.com/science/article/pii/S156984322400685X
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!