A recurrent generator with optical-flow warping and a learned fusion mask, trained with content and temporal losses, improves semantic and temporal consistency in unpaired video translation.
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
-
Preserving Semantic and Temporal Consistency for Unpaired Video-to-Video Translation
A recurrent generator with optical-flow warping and a learned fusion mask, trained with content and temporal losses, improves semantic and temporal consistency in unpaired video translation.