MADNet combines multi-scale pyramid inputs, a learnable frequency mask, and global feature fusion to obtain small PSNR improvements on synthetic and real image denoising benchmarks.
Title resolution pending
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
-
Learning Multi-scale Spatial-frequency Features for Image Denoising
MADNet combines multi-scale pyramid inputs, a learnable frequency mask, and global feature fusion to obtain small PSNR improvements on synthetic and real image denoising benchmarks.