A training strategy that reuses long-sequence hidden states during short-clip backpropagation, combined with ReLU-squared attention and a gated FFN, lifts video super-resolution accuracy to a reported state of the art.
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
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution
A training strategy that reuses long-sequence hidden states during short-clip backpropagation, combined with ReLU-squared attention and a gated FFN, lifts video super-resolution accuracy to a reported state of the art.