期刊文献+

改进可逆缩放网络的图像超分辨率重建

Image Super-Resolution Reconstruction with Improved Invertible Rescaling Network
下载PDF
导出
摘要 可逆缩放网络(IRN)的潜变量采用高斯分布嵌入图像高频信息,因其独立随机性无法充分保存图像高频信息,嵌入效果一般,影响重建性能。通过改进可逆缩放网络来提高嵌入高频信息的能力并进一步降低模型的复杂度。首先,特征提取模块采用密集连接结构和通道注意力机制来获取足够的特征信息,同时减少模块参数量;其次,网络的潜变量采用小波域高频子带插值设计,改善高频信息嵌入能力。实验结果显示该算法相比IRN,在Set5、Set14、BSD100和Urban100这4个基准测试集上的PSNR和SSIM分别平均提升了0.380 dB和0.014,参数量减少约1.64×10^(6),计算量减少约0.43×10^(9),运行时间减少3 ms。表明该算法的重建性能优良,模型复杂度低,具有实用价值。 The latent variable of Invertible Rescaling Network(IRN)uses Gaussian distribution to embed the high-frequency information of the image.Because of the independence and randomness of this approach,the high-frequency information of the image cannot be fully preserved,and the embedding effect is general,which affects the performance of the reconstruction.In order to improve the ability of embedding high frequency information and further reduce the complexity of the model,this paper proposes an improved algorithm based on IRN.Firstly,the dense connection structure and channel attention mechanism are adopted to obtain sufficient feature information and reduce the number of parameters in the feature extraction module.Secondly,the latent variable of the network is designed by high frequency sub-band interpolation in wavelet domain to improve the embedding ability of high frequency information.The results show that compared with IRN,the average Peak Signal to Noise Ratio(PSNR)and Structure Similarity Index Measure(SSIM)of the proposed algorithm are improved by 0.380 dB and 0.014 on the four benchmark test sets Set5,Set14,BSD100 and Urban100,the algorithm parameters in this paper are reduced by about 1.64×10^(6) M,the FLOPs are reduced by about 0.43×10^(9) G,and the running time is reduced by 3 ms.It verifies that the reconstruction performance of the proposed algorithm is excellent and the model complexity is low,which has practical value.
作者 莫太平 黄巧人 陈德鸿 伍锡如 张向文 MO Taiping;HUANG Qiaoren;CHEN Dehong;WU Xiru;ZHANG Xiangwen(School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin Guangxi 541000)
出处 《电子科技大学学报》 EI CAS CSCD 北大核心 2023年第5期739-746,共8页 Journal of University of Electronic Science and Technology of China
基金 国家自然科学基金(61863007) 广西自然科学基金(2020GXNSFDA238029)。
关键词 小波变换 可逆缩放网络 超分辨率重建 注意力机制 attention mechanism invertible rescaling network super-resolution reconstruction wavelet transform
  • 相关文献

参考文献1

二级参考文献3

共引文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部