A depth-based occlusion mask, included as a penalty in the photometric loss, yields a modest improvement in self-supervised monocular depth prediction on KITTI.
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
-
Improving Self-Supervised Single View Depth Estimation by Masking Occlusion
A depth-based occlusion mask, included as a penalty in the photometric loss, yields a modest improvement in self-supervised monocular depth prediction on KITTI.