DCT2net: an interpretable shallow CNN for image denoising - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Image Processing Year : 2022

DCT2net: an interpretable shallow CNN for image denoising


This work tackles the issue of noise removal from images, focusing on the well-known DCT image denoising algorithm. The latter, stemming from signal processing, has been well studied over the years. Though very simple, it is still used in crucial parts of state-of-the-art "traditional" denoising algorithms such as BM3D. Since a few years however, deep convolutional neural networks (CNN) have outperformed their traditional counterparts, making signal processing methods less attractive. In this paper, we demonstrate that a DCT denoiser can be seen as a shallow CNN and thereby its original linear transform can be tuned through gradient descent in a supervised manner, improving considerably its performance. This gives birth to a fully interpretable CNN called DCT2net. To deal with remaining artifacts induced by DCT2net, an original hybrid solution between DCT and DCT2net is proposed combining the best that these two methods can offer; DCT2net is selected to process non-stationary image patches while DCT is optimal for piecewise smooth patches. Experiments on artificially noisy images demonstrate that two-layer DCT2net provides comparable results to BM3D and is as fast as DnCNN algorithm composed of more than a dozen of layers.
Fichier principal
Vignette du fichier
DCT2Net-HAL.pdf (5.5 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03511641 , version 1 (05-01-2022)





Sébastien Herbreteau, Charles Kervrann. DCT2net: an interpretable shallow CNN for image denoising. IEEE Transactions on Image Processing, 2022, 31, pp.4292 - 4305. ⟨10.1109/TIP.2022.3181488⟩. ⟨hal-03511641⟩
100 View
46 Download



Gmail Facebook X LinkedIn More