An RNN-based super-resolution model sequentially predicts Fourier components, letting users trade quality against computation at test time by choosing the number of components.
Enhanced deep resid- ual networks for single image super-resolution,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Test-time Cost-and-Quality Controllable Arbitrary-Scale Super-Resolution with Variable Fourier Components
An RNN-based super-resolution model sequentially predicts Fourier components, letting users trade quality against computation at test time by choosing the number of components.