Article Dans Une Revue IEEE Signal Processing Letters Année : 2021

Fast, nonlocal and neural: a lightweight high quality solution to image denoising

Yu Guo
Axel Davy
Gabriele Facciolo
Jean-Michel Morel
Qiyu Jin

Résumé

With the widespread application of convolutional neural networks (CNNs), the traditional model based denoising algorithms are now outperformed. However, CNNs face two problems. First, they are computationally demanding, which makes their deployment especially difficult for mobile terminals. Second, experimental evidence shows that CNNs often over-smooth regular textures present in images, in contrast to traditional nonlocal models. In this letter, we propose a solution to both issues by combining a nonlocal algorithm with a lightweight residual CNN. This solution gives full latitude to the advantages of both models. We apply this framework to two GPU implementations of classic nonlocal algorithms (NLM and BM3D) and observe a substantial gain in both cases, performing better than the state-of-the-art with low computational requirements. Our solution is between 10 and 20 times faster than CNNs with equivalent performance and attains higher PSNR. In addition the final method shows a notable gain on images containing complex textures like the ones of the MIT Moiré dataset.

Fichier principal
Vignette du fichier
spl.pdf (13.77 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03521188 , version 1 (11-01-2022)

Licence

Identifiants

Citer

Yu Guo, Axel Davy, Gabriele Facciolo, Jean-Michel Morel, Qiyu Jin. Fast, nonlocal and neural: a lightweight high quality solution to image denoising. IEEE Signal Processing Letters, 2021, 28, pp.1515-1519. ⟨10.1109/LSP.2021.3099963⟩. ⟨hal-03521188⟩
168 Consultations
319 Téléchargements

Altmetric

Partager

  • More