A frequency-separated dual-branch transformer with a learnable fusion module reports state-of-the-art or near-state-of-the-art demoiréing on FHDMi and UHDM with only about 6 million parameters.
Image demoireing with learnable bandpass filters
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
background 1representative citing papers
citing papers explorer
-
Freqformer: Image-Demoir\'eing Transformer via Efficient Frequency Decomposition
A frequency-separated dual-branch transformer with a learnable fusion module reports state-of-the-art or near-state-of-the-art demoiréing on FHDMi and UHDM with only about 6 million parameters.