A multi-task network that feeds semantic features into stereo matching and adds two explicit semantic consistency losses achieves state-of-the-art results on US3D and WHU.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SemStereo: Semantic-Constrained Stereo Matching Network for Remote Sensing
A multi-task network that feeds semantic features into stereo matching and adds two explicit semantic consistency losses achieves state-of-the-art results on US3D and WHU.