A self-supervised deep network denoises consumer depth maps by using multi-view color consistency as the training signal, removing the need for ground truth depth.
Fast MRF optimization with application to depth reconstruction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Self-Supervised Deep Depth Denoising
A self-supervised deep network denoises consumer depth maps by using multi-view color consistency as the training signal, removing the need for ground truth depth.