现代信息科技2025，Vol.9Issue(6)：62-66,5.DOI:10.19850/j.cnki.2096-4706.2025.06.012
基于深度学习和小波变换的图像超分辨率方法
Image Super-Resolution Method Based on Deep Learning and Wavelet Transform
黄玉凤 1张小波2
作者信息
- 1. 西安石油大学,陕西 西安 710065
- 2. 西安石油大学,陕西 西安 710065||咸阳师范学院,陕西 咸阳 712000
- 折叠
摘要
Abstract
In recent years,single image Super-Resolution methods based on Deep Learning have achieved remarkable achievements.However,many methods only study the image spatial domain,ignoring the importance of high-frequency information in the image frequency domain,resulting in a relatively smooth image.Because wavelet transform can extract image details,this paper proposes a single image Super-Resolution method combining wavelet transform and Deep Learning.The method processes the image through dynamic convolution,uses Haar wavelet to decompose the image into low-frequency subgraphs and high-frequency subgraphs in three directions,and employs connected residual dense blocks and residual blocks to construct the inference network.Then,the local features are enhanced by inverse wavelet transform and residual dense blocks to obtain Super-Resolution images.The experimental results show that the method performs well in both subjective visual effects and objective evaluation indicators.关键词
超分辨率/小波变换/深度学习/残差密集块/残差块Key words
Super-Resolution/wavelet transform/Deep Learning/residual dense block/residual block分类
信息技术与安全科学引用本文复制引用
黄玉凤,张小波..基于深度学习和小波变换的图像超分辨率方法[J].现代信息科技,2025,9(6):62-66,5.
