Convolutional Nonlinear Dictionary with Cascaded Structure Filter Banks
This work addresses the need for more efficient and structured convolutional neural networks in image restoration, though it appears incremental as it builds on existing CNN frameworks.
The authors tackled the problem of designing structured convolutional networks for image restoration by proposing a convolutional nonlinear dictionary (CNLD) with cascaded filter banks, which reduced the number of parameters while maintaining restoration performance.
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.