CWNet mixes wavelet-based frequency enhancement, Mamba-style high-frequency scanning, and two semantic consistency losses to produce competitive low-light image enhancement with 1.23 million parameters.
Fast fourier convolu- tion
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
-
CWNet: Causal Wavelet Network for Low-Light Image Enhancement
CWNet mixes wavelet-based frequency enhancement, Mamba-style high-frequency scanning, and two semantic consistency losses to produce competitive low-light image enhancement with 1.23 million parameters.