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...

詳細記述

書誌詳細

主要な著者:	Jiwei Liu, Yunzhou Zhang, Jiahua Cui, Yonghui Feng, Linzhuo Pang
フォーマット:	Artigo
言語:	Inglês
出版事項:	Wiley 2019-08-01
シリーズ:	IET Computer Vision
主題:	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
オンライン･アクセス:	https://doi.org/10.1049/iet-cvi.2018.5645
タグ:	タグ追加 タグなし, このレコードへの初めてのタグを付けませんか!