A non-learning method segments an image and gives each region its own scale and shift, fitted to a few sparse depth points, to turn relative monocular depth predictions into metric depth more accurately than a single global scaling.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Region-aware Depth Scale Adaptation with Sparse Measurements
A non-learning method segments an image and gives each region its own scale and shift, fitted to a few sparse depth points, to turn relative monocular depth predictions into metric depth more accurately than a single global scaling.