基于蓝图可分离残差蒸馏网络的图像超分辨率重建

熊荣盛; 王帮海; 杨夏宁

doi:10.12052/gdutxb.230022

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于蓝图可分离残差蒸馏网络的图像超分辨率重建

计算机科学与技术 | 更新时间：2026-05-27

- 基于蓝图可分离残差蒸馏网络的图像超分辨率重建
- Super-resolution Reconstruction of Images Based on Blueprint Separable Residual Distillation Network
- 广东工业大学学报 2024年41卷第2期页码：65-72
- 作者机构：
  
  广东工业大学计算机学院,广东,广州,510006
- 作者简介：
  
  熊荣盛(1996–)，男，硕士研究生，主要研究方向为图像超分辨率重建、深度学习、行人重识别等，E-mail：842524587@qq.com
  王帮海(1974–)，男，教授，博士，主要研究方向为量子纠缠、机器学习等，E-mail：bhwang@gdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(62072119)
- DOI：10.12052/gdutxb.230022
  中图分类号： TP391
- 网络首发：2024-03-25，
  
  纸质出版：2024
- 稿件说明：
移动端阅览
熊荣盛, 王帮海, 杨夏宁. 基于蓝图可分离残差蒸馏网络的图像超分辨率重建[J]. 广东工业大学学报, 2024, 41(2): 65-72.

Xiong Rong-sheng, Wang Bang-hai, Yang Xia-ning. Super-resolution Reconstruction of Images Based on Blueprint Separable Residual Distillation Network[J]. 2024, 41(2): 65-72.
熊荣盛, 王帮海, 杨夏宁. 基于蓝图可分离残差蒸馏网络的图像超分辨率重建[J]. 广东工业大学学报, 2024, 41(2): 65-72. DOI： 10.12052/gdutxb.230022.

Xiong Rong-sheng, Wang Bang-hai, Yang Xia-ning. Super-resolution Reconstruction of Images Based on Blueprint Separable Residual Distillation Network[J]. 2024, 41(2): 65-72. DOI： 10.12052/gdutxb.230022.

摘要

标准卷积的单图像超分辨率重建性能受限于堆叠网络层的冗余性，算法难以实施，特征提取层单一的残差结构也无法高效地利用卷积得到的特征信息。为改善上述问题，本文改进残差蒸馏结构，提出残差蒸馏复用模块，以减少残差蒸馏过程中图像高频信息的损失；此外，将基础残差块替换为蓝图可分离卷积，解耦特征图的空间相关性，以降低高相关性特征的权重，提高卷积的效率，降低参数量。为验证算法的性能，在Set5等标准数据集中对算法进行验证。实验结果表明，该算法模型的峰值信噪比(Peak Signal-To-Noise Ratio

PSNR)和结构相似度(Structural Similarity

SSIM)相比于基于残差蒸馏网络的轻量级图像超分辨率重建网络分别有0.06~0.25 dB与0.004~0.012的提升。

Abstract

The performance of single image super-resolution reconstruction based on standard convolution is limited by the redundancy of the stacked network layers

making it difficult to implement the algorithm on the ground. Moreover

the single residual structure of the feature extraction layer cannot efficiently utilize the feature information obtained from convolution. To address these

this paper proposes a residual distillation reuse module based on the existing residual distillation-based structure to reduce the high-frequency information of the image lost in the residual distillation process. In addition

the base residual block is replaced by a blueprint separable convolution to decouple the spatial correlation of the feature map

such that the weight of highly correlated features can be reduced. As a result

the efficiency of convolution can be improved and the number of parameters can be reduced. We conduct comparative experiments on standard datasets such as Set5 to evaluate the proposed algorithm. The experimental results show that the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) of the proposed algorithm can be improved by approximately 0.06~0.25 dB and 0.004~0.012

respectively

over the lightweightresidual distillation image super-resolution networks.

关键词

Keywords

references

LI J Q, ZHAO Y X, WANG J H. A review of single image super-resolution reconstruction algorithms based on deep learning[J]. Journal of Automation, 2021, 47(10) : 341-2363.

LI X G, FENG X X, LI J X. Multi-scale residual networks for single image super-resolution reconstruction [J]. Computer Engineering and Applications, 2021, 57(7): 215-221.

LU F, ZHOU L, CAI X H. Research on low-resolution face recognition algorithm for security surveillance scenarios [J]. Computer Application Research, 2021, 38(4): 1230-1234.

XIE H P, XIE K L, YANG H T. Research progress of image super-resolution methods [J]. Computer Engineering and Applications, 2020, 56(19): 34-41.

LI Q, WANG X Y, HE J W. An improved algorithm for super-resolution reconstruction of remote sensing images based on generative adversarial networks [J]. Advances in Laser and Optoelectronics, 2023, 37(5): 1-14.

XIAO C L. A histogram balanced interpolation-based detail enhancement method for pelvic floor ultrasound images [J]. Automation and Instrumentation, 2022(6): 261-264.

LLU J M, ZHENG C, ZHANG L M, et al . Hyperspectral image classification method based on image reconstruction feature fusion [J ] . China Las er, 2021, 48(9): 203-212.

WANG Z, CHEN J, HOU S. Deep learning for image super-resolution: a survey [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(10): 3365-3387.

LIU C, QU D, SI N W, et al . Lightweight image super-resolution reconstruction based on depth-separable convolution [J ] . Computer Engineering, 2022, 48(6): 228-234.

HU C S, ZHAN S, WU C Z. Deep feature learning based image super-resolution reconstruction [J]. Journal of Automation, 2017, 43(5): 814-821.

WU J, YE X J, HUANG F, et al . A review of single frame image super-resolution reconstruction based on deep learning [J ] . Journal of Electronics, 2022, 50(9): 2265-2294.

LI X, LIU L Z. Multi-branch residual feature distillation network for image super-resolution reconstruction [J]. Small Microcomputer Systems, 2023, 48(3): 1-9.

CHAO D, CHEN C L, HE K, et al . Learning a deep convolutional network for image super-resolution[C ] //ECCV Springer International Publishing. Istanbul: Springer Cham, 2014: 184-199.

KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks[C]//IEEE Conference on Computer Vision Pattern Recognition(CVPR) . Las Vegas: IEEE, 2016: 1646-1654.

LIM B, SON S, KIM H, et al. Enhanced deep residual networks for single image super- resolution[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops(CVPRW) . Honolulu: IEEE, 2017: 1132-1140.

KIM J, LEE J K, LEE K M. Deeply-recursive convolutional network for image super- resolution[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR) . Las Vegas: IEEE, 2016: 1637-1645.

YING T, JIAN Y, LIU X. Image super-resolution via deep recursive residual network[C]//IEEE Conference on Computer Vision Pattern Recognition(CVPR) . Honolulu: IEEE, 2017: 2790-2798.

TAI Y, YANG J, LIU X, et al . MemNet: a persistent memory network for image restoration[C ] //IEEE International Conference on Computer Vision. Venice: IEEE Computer Society, 2017: 4549-4557.

AHN N, KANG B, SOHN K A. Fast, accurate, and lightweight super-resolution with cascading residual network[C]//Computer Vision ECCV 2018 15th European Conference. Martial: ECCV, 2018: 256-272.

ZHENG H, WANG X, GAO X . Fast and accurate single image super-resolution via information distillation network[C]//Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 723-731.

HUI Z, GAO X , YANG Y , et al . Lightweight image super-resolution with information multi-distillation network[C ] //Proceedings of the 27th ACM International Conference on Multimedia. France: ACM, 2019: 2024-2032.

LIU J, TANG J, WU G. Residual feature distillation network for lightweight image super-resolution[C]//2020 ECCV Springer International Publishing. UK: Springer Cham, 2020: 41-55.

HOWARD A G, ZHU M, CHEN B, et al . MobileNets: efficient convolutional neural networks for mobile vision applications[C ] // Conference on Computer Vision and Pattern Recognition(CVPR) . Honolulu: IEEE, 2017: 112-121.

HAASE D, AMTHOR M. Rethinking depthwise separable convolutions: how intra-kernel correlations lead to Improved mobileNets[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) . Seattle: IEEE, 2020: 14588-14597 .

GUO J, LI Y, LIN W , et al . Network decoupling: fom regular to depthwise separable convolutions[C ] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR) . Salt Lake City: IEEE, 2018: 1879-1901.

ZHANG Y, LI K, LI K , et al . Image super-resolution using very deep residual channel attention networks[C ] //Proceedings of the European Conference on Computer Visionand Pattern Recognition(CVPR) . Munich: Springer, Cham, 2018: 286-301.

WANG Q , WU B , ZHU P , et al . ECA-net: efficient channel attention for deep convolutional neural networks[C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Seattle: IEEE, 2020: 11531-11539.

SUN L, PAN J, TANG J. ShuffleMixer: an efficient convNet for image super-resolution[C]//IEEE International Conference on Computer Vision. Hawaii: IEEE Computer Society, 2022: 321-329.

KONG F , LI M , LIU S , et al . Residual local feature network for efficient super-resolution[C ] //2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . New Orleans: IEEE, 2022: 765-775.

LI Z, LIU Y, CHEN X, et al . Blueprint separable residual network for efficient image super-resolution[C ] //2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . New Orleans: IEEE, 2022: 832-842.

ZHANG Y, TIAN Y, KONG Y, et al . Residual dense network for image super-resolution[C ] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Munich: IEEE, 2018: 2472-2481.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

用于三维点云分割和分类的高分辨率特征网络

基于改进Unet网络的锂电池极片表面缺陷检测

基于局部正交特征融合的小样本图像分类

基于YOLOv4-MP的绝缘子爆裂缺陷检测方法

基于特征融合的深度学习目标检测算法研究