Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Real Image Denoising with Feature Attention

About

Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, their performance is limited on real-noisy photographs and requires multiple stage network modeling. To advance the practicability of denoising algorithms, this paper proposes a novel single-stage blind real image denoising network (RIDNet) by employing a modular architecture. We use a residual on the residual structure to ease the flow of low-frequency information and apply feature attention to exploit the channel dependencies. Furthermore, the evaluation in terms of quantitative metrics and visual quality on three synthetic and four real noisy datasets against 19 state-of-the-art algorithms demonstrate the superiority of our RIDNet.

Saeed Anwar, Nick Barnes• 2019

Related benchmarks

TaskDatasetResultRank
Gray-scale image denoisingSet12
PSNR32.91
131
Image DenoisingSIDD (val)
PSNR38.76
105
Image DenoisingBSD68 grayscale (test)
PSNR31.81
101
Image DenoisingDND
PSNR39.26
99
Image DenoisingSIDD (test)
PSNR38.71
97
Image DenoisingSIDD
PSNR38.71
95
Image DenoisingDND (test)
PSNR39.26
94
Gaussian DenoisingBSD68
PSNR31.81
89
Image DenoisingSIDD 1 (test)
PSNR38.71
89
Color Image DenoisingKodak24 (test)
PSNR31.64
79
Showing 10 of 79 rows
...

Other info

Follow for update