Fully convolutional multi‐scale dense networks for monocular depth estimation

Monocular depth estimation is of vital importance in understanding the 3D geometry of a scene. However, inferring the underlying depth is ill‐posed and inherently ambiguous. In this study, two improvements to existing approaches are proposed. One is about a clean improved network architecture, for w...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Jiwei Liu, Yunzhou Zhang, Jiahua Cui, Yonghui Feng, Linzhuo Pang
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	Wiley 2019-08-01
סדרה:	IET Computer Vision
נושאים:	clean improved network architecture end-to-end fully convolutional multiscale dense networks dense upsampling blocks selected skip connection edge-preserving loss functions reverse Huber loss
גישה מקוונת:	https://doi.org/10.1049/iet-cvi.2018.5645
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!