基于非对称信息蒸馏网络的轻量级图像超分辨重建  

Lightweight image super-resolution reconstruction based on asymmetric information distillation network

作　　者：孟海腾 赵小乐 李天瑞[1] MENG Haiteng;ZHAO Xiaole;LI Tianrui(School of Computing and Artificial Intelligence,Southwest Jiaotong University,Chengdu Sichuan 611756,China)

机构地区：[1]西南交通大学计算机与人工智能学院,成都611756

出　　处：《计算机应用》2025年第2期601-609,共9页journal of Computer Applications

基　　金：国家自然科学基金资助项目(62102330)。

摘　　要：深度卷积神经网络(CNN)在图像超分辨率重建领域表现出卓越性能,然而现有的许多相关方法的模型参数量较多,无法应用至计算资源较低的设备。为缓解上述问题,提出一个轻量级的非对称信息蒸馏网络(AIDN)模型。首先,输入原始图像及其边缘图像以提取有效的特征信息;其次,设计一个非对称信息蒸馏块对提取到的特征进行非线性映射学习;再次,使用上采样模块重建多个残差图像后,将这些残差图像经过注意力机制融合成一个残差图像;最后,将融合的残差图像与输入图像的插值相加后得到超分图像。在Set14、Urban100和Manga109数据集上的实验结果表明,相较于空间自适应特征调制网络(SAFMN),AIDN模型的4倍超分峰值信噪比(PSNR)值分别提升了0.03 dB、0.14 dB和0.06 dB,说明了AIDN模型在模型参数量和模型性能之间取得了更好的平衡。Deep Convolutional Neural Network(CNN)has impressive performance in image super-resolution reconstruction.However,many current related methods have a lot of model parameters,making them unsuitable for devices with limited computational resources.To address the above problem,a lightweight Asymmetric Information Distillation Network(AIDN)was proposed.Firstly,effective feature information was extracted from the input original images and edge images.Secondly,an asymmetric information distillation module was designed for non-linear mapping learning on these features.Thirdly,multiple residual images were reconstructed by an upsampling module and fused into one residual image through attention mechanism.Finally,the fused residual image was added to the interpolation of the input image to generate the super-resolution image.Experimental results on Set14,Urban100,and Manga109 datasets show that the 4×superresolution Peak Signal-to-Noise Ratio(PSNR)values of AIDN model are improved by 0.03 dB,0.14 dB,and 0.06 dB,respectively,compared to those of Spatial Adaptive Feature Modulation Network(SAFMN).This demonstrates that AIDN model achieves a superior balance between model parameters and performance.

关 键 词：图像超分辨率 轻量级超分辨率网络 非对称卷积 信息蒸馏 注意力机制 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]