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...

Ful tanımlama

Kaydedildi:

Detaylı Bibliyografya
Asıl Yazarlar:	Jiwei Liu, Yunzhou Zhang, Jiahua Cui, Yonghui Feng, Linzhuo Pang
Materyal Türü:	Artigo
Dil:	Inglês
Baskı/Yayın Bilgisi:	Wiley 2019-08-01
Seri Bilgileri:	IET Computer Vision
Konular:	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
Online Erişim:	https://doi.org/10.1049/iet-cvi.2018.5645
Etiketler:	Etiketle Etiket eklenmemiş, İlk siz ekleyin!

Fully convolutional multi‐scale dense networks for monocular depth estimation

Benzer Materyaller