摘要
Abstract
In the task of image super-resolution reconstruction,this paper proposes an image super-resolution method called MSA-SR,which is based on multi-scale features and attention mechanisms.This method effectively captures the low-fre-quency and high-frequency features of low-resolution images by separating and extracting multi-scale features in both the time and frequency domains.On this basis,high-frequency guided cross-attention is used to selectively enhance high-frequency features,while wavelet convolution is employed to protectively enhance low-frequency features,achieving clear and natural image super-resolution reconstruction effects.The model was validated on the Urban100 and Manga109 datasets,and its per-formance metrics of Peak Signal-to-Noise Ratio(PSNR)and Structural Similarity(SSIM)showed certain advantages over other deep learning super-resolution methods.From a quality perception perspective,this model has made significant im-provements in texture recovery,color restoration,noise suppression,and naturalness of the image,achieving superior visual effects,which proves the effectiveness and superiority of the model.关键词
图像超分辨率重建/多尺度特征/注意力机制/深度学习/卷积神经网络/高频细节恢复Key words
image super-resolution reconstruction/multi-scale features/attention mechanism/deep learning/convolutional neural networks/high-frequency detail recovery分类
信息技术与安全科学
