Convolutional Nonlinear Dictionary with Cascaded Structure Filter Banks

TL;DR

This paper introduces a convolutional nonlinear dictionary with a cascaded filter bank structure, aiming to improve image restoration by reducing parameters while maintaining performance.

Contribution

It proposes the CNLD framework that considers relationships among convolution kernels, enhancing structured network design for image restoration.

Findings

Reduces parameters without sacrificing restoration quality

Verifies effectiveness through image restoration experiments

Provides a new structured approach to convolutional network design

Abstract

This study proposes a convolutional nonlinear dictionary (CNLD) for image restoration using cascaded filter banks. Generally, convolutional neural networks (CNN) demonstrate their practicality in image restoration applications; however, existing CNNs are constructed without considering the relationship among atomic images (convolution kernels). As a result, there remains room for discussing the role of design spaces. To provide a framework for constructing an effective and structured convolutional network, this study proposes the CNLD. The backpropagation learning procedure is derived from certain image restoration experiments, and thereby the significance of CNLD is verified. It is demonstrated that the number of parameters is reduced while preserving the restoration performance.