用频域注意力提升图像超分辨率细节重建能力
Fourier-Guided Attention Upsampling for Image Super-Resolution
- 通过傅里叶特征编码与跨分辨率注意力实现自适应上采样
- 仅增加0.3M参数，平均提升0.12~0.14 dB PSNR，频域一致性提高29%
- 适合需要细节还原的轻量级或高精度超分任务
我们提出频率引导注意力（FGA），一种用于单图像超分辨率的轻量级上采样模块。传统上采样方法如子像素卷积虽高效，但常无法重建高频细节并引入混叠伪影。FGA通过三个设计解决此问题：(1) 基于傅里叶特征的多层感知机（MLP）进行位置频率编码，(2) 跨分辨率相关性注意力层实现自适应空间对齐，(3) 频域L1损失监督频谱保真度。仅增加0.3M参数，FGA在五个不同超分辨率骨干网络中均稳定提升性能，无论轻量或全容量场景。实验显示平均PSNR提升0.12~0.14 dB，频域一致性最高提升29%，尤其在纹理丰富数据集上表现显著。视觉与频域评估证实其能有效减少混叠、保留细粒度结构，是传统上采样方法的实用且可扩展替代方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。