QR-koodi

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...

Täydet tiedot

Tallennettuna:
Päätekijät: Jiwei Liu, Yunzhou Zhang, Jiahua Cui, Yonghui Feng, Linzhuo Pang
Aineistotyyppi: Artigo
Kieli:Inglês
Julkaistu: Wiley 2019-08-01
Sarja:IET Computer Vision
Aiheet:
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
Linkit:https://doi.org/10.1049/iet-cvi.2018.5645
Tagit: Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!

Samankaltaisia teoksia