用大卷积核模拟自注意力，实现高效图像超分辨率。
LKFMixer: Exploring Large Kernel Feature For Efficient Image Super-Resolution
- 大卷积核配合坐标分解，低计算量捕捉全局特征。
- ×4缩放下比SwinIR-light高0.6dB PSNR，速度提升5倍。
- 适合追求轻量化与高速推理的图像重建场景。
Transformer中自注意力的成功证明了非局部信息对图像超分辨率的重要性，但其计算开销过大，难以部署轻量级模型。为此，本文提出纯卷积神经网络LKFMixer，通过大卷积核模拟自注意力的全局建模能力。具体地，将卷积核尺寸增至31以最大化感受野，并采用坐标分解降低参数与计算量。设计空间特征调制块（SFMB）增强空间与通道维度的特征聚焦能力。引入特征选择块（FSB），自适应调整局部与非局部特征权重。大量实验表明，所提LKFMixer系列在超分辨率性能与重建质量上优于现有SOTA方法。尤其在Manga109数据集×4缩放下，相比SwinIR-light，LKFMixer-L提升0.6dB PSNR，推理速度加快5倍。代码已开源。
原文摘要 · Abstract (English)
The success of self-attention (SA) in Transformer demonstrates the importance of non-local information to image super-resolution (SR), but the huge computing power required makes it difficult to implement lightweight models. To solve this problem, we propose a pure convolutional neural network (CNN) model, LKFMixer, which utilizes large convolutional kernel to simulate the ability of self-attention to capture non-local features. Specifically, we increase the kernel size to 31 to obtain the larger receptive field as possible, and reduce the parameters and computations by coordinate decomposition. Meanwhile, a spatial feature modulation block (SFMB) is designed to enhance the focus of feature information on both spatial and channel dimension. In addition, by introducing feature selection block (FSB), the model can adaptively adjust the weights between local features and non-local features. Extensive experiments show that the proposed LKFMixer family outperform other state-of-the-art (SOTA) methods in terms of SR performance and reconstruction quality. In particular, compared with SwinIR-light on Manga109 dataset, LKFMixer-L achieves 0.6dB PSNR improvement at $\times$4 scale, while the inference speed is $\times$5 times faster. The code is available at https://github.com/Supereeeee/LKFMixer.
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。