JFFRA jointly refines optical flow and frame features in an iterative attention-based loop, reporting gains up to 1.62 dB over prior video restoration methods.
Basicvsr++: Improving video super- resolution with enhanced propagation and alignment
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Joint Flow And Feature Refinement Using Attention For Video Restoration
JFFRA jointly refines optical flow and frame features in an iterative attention-based loop, reporting gains up to 1.62 dB over prior video restoration methods.