CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing

Nikola Janjusevic, Amirhossein Khalilian-Gourtani, Yao Wang

Research output: Contribution to journalArticlepeer-review

Abstract

Deep learning based methods hold state-of-the-art results in low-level image processing tasks, but remain difficult to interpret due to their black-box construction. Unrolled optimization networks present an interpretable alternative to constructing deep neural networks by deriving their architecture from classical iterative optimization methods without use of tricks from the standard deep learning tool-box. So far, such methods have demonstrated performance close to that of state-of-the-art models while using their interpretable construction to achieve a comparably low learned parameter count. In this work, we propose an unrolled convolutional dictionary learning network (CDLNet) and demonstrate its competitive denoising and joint denoising and demosaicing (JDD) performance both in low and high parameter count regimes. Specifically, we show that the proposed model outperforms state-of-the-art fully convolutional denoising and JDD models when scaled to a similar parameter count. In addition, we leverage the model's interpretable construction to propose a noise-adaptive parameterization of thresholds in the network that enables state-of-the-art blind denoising performance, and near-perfect generalization on noise-levels unseen during training. Furthermore, we show that such performance extends to the JDD task and unsupervised learning.

Original languageEnglish (US)
Pages (from-to)196-211
Number of pages16
JournalIEEE Open Journal of Signal Processing
Volume3
DOIs
StatePublished - 2022

Keywords

  • Interpretable deep learning
  • blind denoising
  • dictionary learning
  • joint demosaicing and denoising
  • sparse coding
  • unrolled networks

ASJC Scopus subject areas

  • Signal Processing

Fingerprint

Dive into the research topics of 'CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing'. Together they form a unique fingerprint.

Cite this