A multiscale dilated convolution and mixed-order attention-based deep neural network for monocular depth prediction

A multiscale dilated convolution and mixed-order attention-based deep neural network for monocular depth prediction

Article Highlights We designed an efficient monocular depth prediction framework on the basis of multiscale dilated convolution and a mixed-order attention mechanism. This framework can produce effective depth outputs with rich details. Our mixed-order attention-based feature enhancement module can...

Full description

Bibliographic Details
Main Authors: Huihui Xu, Fei Li
Format: Article
Language:English
Published: Springer 2022-12-01
Series:SN Applied Sciences
Subjects:
Depth prediction
Feature enhancement
Attention mechanism
Dilated convolution
Online Access:https://doi.org/10.1007/s42452-022-05235-1

Internet

https://doi.org/10.1007/s42452-022-05235-1

Similar Items