电子科技2026，Vol.39Issue(10)：52-62,11.DOI:10.16180/j.cnki.issn1007-7820.2026.10.006
基于特征调制蒸馏网络的图像超分辨率重建
Image Super-Resolution Reconstruction Based on Feature Modulation Distillation Network
摘要
Abstract
In view of the problem that image super-resolution algorithms are difficult to be applied to low-per-formance devices due to their high model complexity,a lightweight feature modulation distillation network is de-signed.A feature modulation purification module is proposed,which efficiently purifies features through dual-branch aggregation to simplify the model structure.The improved hybrid attention module further enhances feature representation in both spatial and channel dimensions.The lightweight bidirectional progressive upsampling module effectively reduces the model complexity during feature reconstruction through dual-stage upsampling in both hori-zontal and vertical directions.The experimental results show that the performance of the proposed algorithm is supe-rior to the existing methods,achieving a good balance between model complexity and reconstruction performance.In the×2 super-resolution tasks of five benchmark test sets,compared with the information distillation network,the peak signal-to-noise ratio of the proposed algorithm is increased by an average of approximately 0.45 dB,while the number of parameters and the multiply-add cumulative computational complexity are only 44%and 41%respective-ly.关键词
卷积神经网络/高效图像超分辨率/特征调制/信息蒸馏/轻量化上采样/注意力机制Key words
convolutional neural network/efficient image super-resolution/feature modulation/information distillation/lightweight upsampling/attention mechanism分类
信息技术与安全科学引用本文复制引用
陈鹏民,陈清江..基于特征调制蒸馏网络的图像超分辨率重建[J].电子科技,2026,39(10):52-62,11.基金项目
国家自然科学基金(12101482) National Natural Science Foundation of China(12101482) （12101482）
