A deep neural network learns depth and hierarchical feature maps from monocular video, and camera pose is computed by aligning those features directly, preserving metric scale.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unsupervised Learning of Depth and Deep Representation for Visual Odometry from Monocular Videos in a Metric Space
A deep neural network learns depth and hierarchical feature maps from monocular video, and camera pose is computed by aligning those features directly, preserving metric scale.