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

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.

References in corpus (11)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Learned Primal-dual Reconstruction
• Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
• Deep Graph-Convolutional Image Denoising
• Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds
• Learned Convolutional Sparse Coding
• Unsupervised Learning with Stein's Unbiased Risk Estimator
• Rethinking the CSC Model for Natural Images
• A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding
• Gabor is Enough: Interpretable Deep Denoising with a Gabor Synthesis Dictionary Prior

Cited by in corpus (3)

• GroupCDL: Interpretable Denoising and Compressed Sensing MRI via Learned Group-Sparsity and Circulant Attention
• Learned Primal Dual Splitting for Self-Supervised Noise-Adaptive MRI Reconstruction
• Self-Supervised Noise Adaptive MRI Denoising via Repetition to Repetition (Rep2Rep) Learning