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.

翻译：本文提出了差分小波放大器（DWA），一种可直接集成到基于小波的图像超分辨率（SR）模型中的模块。DWA 重新激活了近期较少受到关注的离散小波变换（DWT）方法。DWT 能够为 SR 提供高效的图像表示，并将输入的空间区域面积缩小4倍，同时降低模型整体规模和计算成本，使其成为可持续机器学习中极具吸引力的方法。我们提出的 DWA 模型通过利用两个卷积滤波器之间的差异来优化小波域中相关特征的提取，从而突出局部对比度并抑制输入信号中的常见噪声，进而改进了基于小波的 SR 模型。通过将 DWA 集成到现有 SR 模型（例如 DWSR 和 MWCNN）中，我们验证了其有效性，并展示了在经典 SR 任务上的显著性能提升。此外，由于 DWA 省略了传统 DWT，它使得 DWSR 和 MWCNN 能够直接应用于输入图像空间，从而按通道缩减了 DWT 的表示规模。