DWA: Differential Wavelet Amplifier for Image Super-Resolution
This work addresses image super-resolution for applications like sustainable ML, but it is incremental as it builds on existing wavelet-based models.
The paper tackles image super-resolution by proposing a drop-in module called Differential Wavelet Amplifier (DWA) that enhances wavelet-based models, improving performance in classical tasks and reducing model size and computation costs by leveraging differential filters in the wavelet domain.
This work introduces Differential Wavelet Amplifier (DWA), a drop-in module for wavelet-based image Super-Resolution (SR). DWA invigorates an approach recently receiving less attention, namely Discrete Wavelet Transformation (DWT). DWT enables an efficient image representation for SR and reduces the spatial area of its input by a factor of 4, the overall model size, and computation cost, framing it as an attractive approach for sustainable ML. Our proposed DWA model improves wavelet-based SR models by leveraging the difference between two convolutional filters to refine relevant feature extraction in the wavelet domain, emphasizing local contrasts and suppressing common noise in the input signals. We show its effectiveness by integrating it into existing SR models, e.g., DWSR and MWCNN, and demonstrate a clear improvement in classical SR tasks. Moreover, DWA enables a direct application of DWSR and MWCNN to input image space, reducing the DWT representation channel-wise since it omits traditional DWT.