Adding adversarial view-consistent warping supervision to a monocular depth network improves NYU Depth v2 accuracy by about 0.8 percentage points in δ1, with larger gains on a reduced training set.
Depth from a single image by harmonizing overcomplete local network predictions
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
-
Adversarial View-Consistent Learning for Monocular Depth Estimation
Adding adversarial view-consistent warping supervision to a monocular depth network improves NYU Depth v2 accuracy by about 0.8 percentage points in δ1, with larger gains on a reduced training set.