Fourier-Guided Attention Upsampling for Image Super-Resolution
This work addresses the challenge of preserving fine details in super-resolution for applications like image enhancement, offering a practical, scalable alternative to traditional methods, though it is incremental as it builds upon existing upsampling techniques.
The paper tackled the problem of reconstructing high-frequency details and reducing aliasing artifacts in single image super-resolution by proposing a lightweight upsampling module called Frequency-Guided Attention (FGA), which achieved average PSNR gains of 0.12~0.14 dB and improved frequency-domain consistency by up to 29% across diverse backbones.
We propose Frequency-Guided Attention (FGA), a lightweight upsampling module for single image super-resolution. Conventional upsamplers, such as Sub-Pixel Convolution, are efficient but frequently fail to reconstruct high-frequency details and introduce aliasing artifacts. FGA addresses these issues by integrating (1) a Fourier feature-based Multi-Layer Perceptron (MLP) for positional frequency encoding, (2) a cross-resolution Correlation Attention Layer for adaptive spatial alignment, and (3) a frequency-domain L1 loss for spectral fidelity supervision. Adding merely 0.3M parameters, FGA consistently enhances performance across five diverse super-resolution backbones in both lightweight and full-capacity scenarios. Experimental results demonstrate average PSNR gains of 0.12~0.14 dB and improved frequency-domain consistency by up to 29%, particularly evident on texture-rich datasets. Visual and spectral evaluations confirm FGA's effectiveness in reducing aliasing and preserving fine details, establishing it as a practical, scalable alternative to traditional upsampling methods.