Image Super Resolution Algorithm Based on Receptive Field Optimization and Progressive Feature Fusion

WU Hongwu; GAI Shaoyan; DA Feipeng

doi:10.7652/xjtuxb202501013

您当前的位置：

首页 >

文章列表页 >

Image Super Resolution Algorithm Based on Receptive Field Optimization and Progressive Feature Fusion

更新时间：2026-01-06

- Image Super Resolution Algorithm Based on Receptive Field Optimization and Progressive Feature Fusion
- Journal of Xi’an Jiaotong University Vol. 59, Issue 1, Pages: 136-147(2025)
- 作者机构：
  
  1.东南大学自动化学院， 210096，南京
  2.东南大学复杂工程系统测量与控制教育部重点实验室， 210096，南京
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202501013
  CLC： TP391
- Received：07 April 2024，
  
  Online First：18 July 2024，
  
  Published：10 January 2025
- 稿件说明：
移动端阅览
WU Hongwu, GAI Shaoyan, DA Feipeng. Image Super Resolution Algorithm Based on Receptive Field Optimization and Progressive Feature Fusion[J]. Journal of Xi’an Jiaotong University, 2025, 59(1): 136-147.
DOI：

WU Hongwu, GAI Shaoyan, DA Feipeng. Image Super Resolution Algorithm Based on Receptive Field Optimization and Progressive Feature Fusion[J]. Journal of Xi’an Jiaotong University, 2025, 59(1): 136-147. DOI： 10.7652/xjtuxb202501013.

摘要

针对现有基于深度学习的超分辨率方法存在参数冗余以及难以学习到全局上下文信息、重建图像高频特征能力欠佳的问题，提出一种基于感受野优化与渐进特征融合的超分辨率网络（RPSRnet），其在单幅图像重建方面实现了较高的性能。该网络采用像素注意力机制与大感受野卷积相结合的方式，设计两条渐进路径将输入表征为不同层次的特征抽象，增强网络捕获上下文信息的能力，同时减少了网络参数冗余。通过分层卷积和多重感受野分支，在保持轻量卷积的前提下，于分层的多路径上学习不同尺度的融合特征，增强网络重建边缘细节和复杂纹理特征的能力。实验结果表明：相比于先进算法，所提算法在基准测试集Set5上的峰值信噪比达到32.47 dB，在测试集Set14上达到28.81 dB，优于现有的先进算法，且网络参数更少，实现了9%的参数缩减，从而验证了算法的有效性。

Abstract

To tackle the issue of parameter redundancy and the challenge of learning comprehensive global contextual information in current deep learning-based super-resolution methods

as well as the limited capacity to reconstruct high-frequency image features

a super-resolution network (RPSRnet) based on receptive field optimization and progressive feature fusion is proposed

delivering exceptional performance in single image reconstruction. By integrating pixel attention mechanisms and large receptive field convolutions

two progressive pathways are devised to interpret inputs as features at varying levels of abstraction. This design enriches the network's capability to grasp contextual information while streamlining parameter redundancy. Through the utilization of hierarchical convolutions and multiple receptive field branches

the network sustains lightweight convolutions and acquires fused features from diverse scales on hierarchical pathways. This process enhances the network's proficiency in reconstructing edge details and intricate texture features. The experimental results reveal that the proposed algorithm achieves a peak signal-to-noise ratio of 32.47 dB on the Set5 benchmark test set and 28.81 dB on the Set14 test set. The algorithm surpasses existing advanced algorithms

utilizing fewer parameters and resulting in a 9% reduction in parameters

effectively validating the algorithm's efficacy.

关键词

Keywords

references

AAKERBERG A , NASROLLAHI K , MOESLUND T B . Real-world super-resolution of face-images from surveillance cameras [J ] . IET Image Processing , 2022 , 16 ( 2 ): 442 - 452 .

HARIS M , SHAKHNAROVICH G , UKITA N . Task-driven super resolution: object detection in low-resolution images [C ] // Neural Information Processing . Cham, Switzerland : Springer International Publishing , 2021 : 387 - 395 .

李嫣 , 任文琦 , 张长青 , 等 . 基于真实退化估计与高频引导的内窥镜图像超分辨率重建 [J ] . 自动化学报 , 2024 , 50 ( 2 ): 334 - 347 .

LI Yan , REN Wenqi , ZHANG Changqing , et al . Super-resolution of endoscopic images based on real degradation estimation and high-frequency guidance [J ] . Acta Automatica Sinica , 2024 , 50 ( 2 ): 334 - 347 .

徐胜军 , 杜淼 , 段中兴 , 等 . 多尺度区域注意力InfoGAN车牌识别网络 [J ] . 西安交通大学学报 , 2023 , 57 ( 8 ): 206 - 218 .

XU Shengjun , DU Miao , DUAN Zhongxing , et al . Multi-scale regional attention InfoGAN license plate recognition network [J ] . Journal of Xi'an Jiaotong University , 2023 , 57 ( 8 ): 206 - 218 .

CHEN Wenlong , YAO Pengcheng , GAI Shaoyan , et al . Multi-scale feature aggregation network for image super-resolution [J ] . Applied Intelligence , 2022 , 52 ( 4 ): 3577 - 3586 .

韩玉兰 , 顾琴 , 崔玉杰 , 等 . 基于树状多分支残差注意力网络的真实场景图像超分辨率重构 [J ] . 控制与决策 , 2024 , 39 ( 10 ): 3442 - 3450 .

HAN Yulan , GU Qin , CUI Yujie , et al . Real-world super-resolution based on residual attention network with tree based multi-branch structure [J ] . Control and Decision , 2024 , 39 ( 10 ): 3442 - 3450 .

KIM J H , CHOI J H , CHEON M , et al . MAMNet: multi-path adaptive modulation network for image super-resolution [J ] . Neurocomputing , 2020 , 402 : 38 - 49 .

DONG Chao , LOY C C , HE Kaiming , et al . Learning a deep convolutional network for image super-resolution [C ] // Computer Vision-ECCV 2014 . Cham, Switzerland : Springer International Publishing , 2014 : 184 - 199 .

DONG Chao , LOY C C , TANG Xiaoou . Accelerating the super-resolution convolutional neural network [C ] // Computer Vision-ECCV 2016 . Cham, Switzerland : Springer International Publishing , 2016 : 391 - 407 .

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

AHN N , KANG B , SOHN K A . Fast, accurate, and lightweight super-resolution with cascading residual network [C ] // Computer Vision-ECCV 2018 . Cham, Switzerland : Springer International Publishing , 2018 : 256 - 272 .

LIU Jie , TANG Jie , WU Gangshan . Residual feature distillation network for lightweight image super-resolution [C ] // Computer Vision-ECCV 2020 Workshops . Cham, Switzerland : Springer International Publishing , 2020 : 41 - 55 .

KONG Fangyuan , LI Mingxi , LIU Songwei , et al . Residual local feature network for efficient super-resolution [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway, NJ, USA : IEEE , 2022 : 765 - 775 .

梁敏 , 汪西莉 . 结合超分辨率和域适应的遥感图像语义分割方法 [J ] . 计算机学报 , 2022 , 45 ( 12 ): 2619 - 2636 .

LIANG Min , WANG Xili . Semantic segmentation model for remote sensing images combining super resolution and domain adaption [J ] . Chinese Journal of Computers , 2022 , 45 ( 12 ): 2619 - 2636 .

CHEN Haoyu , GU Jinjin , LIU Yihao , et al . Masked image training for generalizable deep image denoising [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway, NJ, USA : IEEE , 2023 : 1692 - 1703 .

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) . Piscataway, NJ, USA : IEEE , 2017 : 1132 - 1140 .

HUI Zheng , GAO Xinbo , YANG Yunchu , et al . Lightweight image super-resolution with information multi-distillation network [C ] // Proceedings of the 27th ACM International Conference on Multimedia . New York, NY, USA : ACM , 2019 : 2024 - 2032 .

LUO Xiaotong , XIE Yuan , ZHANG Yulun , et al . LatticeNet: towards lightweight image super-resolution with lattice block [C ] // Computer Vision-ECCV 2020 . Cham, Switzerland : Springer International Publishing , 2020 : 272 - 289 .

LI Zheyuan , LIU Yingqi , CHEN Xiangyu , et al . Blueprint separable residual network for efficient image super-resolution [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway, NJ, USA : IEEE , 2022 : 832 - 842 .

LIANG Jingyun , CAO Jiezhang , SUN Guolei , et al . SwinIR: image restoration using Swin transformer [C ] // 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) . Piscataway, NJ, USA : IEEE , 2021 : 1833 - 1844 .

LU Zhisheng , LI Juncheng , LIU Hong , et al . Transformer for single image super-resolution [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway, NJ, USA : IEEE , 2022 : 456 - 465 .

CHEN Zheng , ZHANG Yulun , GU Jinjin , et al . Dual aggregation transformer for image super-resolution [C ] // 2023 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway, NJ, USA : IEEE , 2023 : 12278 - 12287 .

WANG Hang , CHEN Xuanhong , NI Bingbing , et al . Omni aggregation networks for lightweight image super-resolution [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway, NJ, USA : IEEE , 2023 : 22378 - 22387 .

CHEN Xiangyu , WANG Xintao , ZHOU Jiantao , et al . Activating more pixels in image super-resolution transformer [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway, NJ, USA : IEEE , 2023 : 22367 - 22377 .

LIU Zhuang , MAO Hanzi , WU Chaoyuan , et al . A ConvNet for the 2020s [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway, NJ, USA : IEEE , 2022 : 11966 - 11976 .

HESSE R , SCHAUB-MEYER S , ROTHS . Content-adaptive downsampling in convolutional neural networks [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway, NJ, USA : IEEE , 2023 : 4544 - 4553 .

GUO Menghao , LU Chengze , LIU Zhengning , et al . Visual attention network [J ] . Computational Visual Media , 2023 , 9 ( 4 ): 733 - 752 .

ZHOU Lin , CAI Haoming , GU Jinjin , et al . Efficient image super-resolution using vast-receptive-field attention [C ] // Computer Vision-ECCV 2022 Workshops . Cham, Switzerland : Springer Nature Switzerland , 2023 : 256 - 272 .

ZHAO Hengyuan , KONG Xiangtao , HE Jingwen , et al . Efficient image super-resolution using pixel attention [C ] // Computer Vision-ECCV 2020 Workshops . Cham, Switzerland : Springer International Publishing , 2020 : 56 - 72 .

HU Jie , SHEN Li , ALBANIE S , et al . Squeeze-and-excitation networks [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2020 , 42 ( 8 ): 2011 - 2023 .

SHANG Jianrun , ZHANG Xue , ZHANG Guisheng , et al . Gated multi-attention feedback network for medical image super-resolution [J ] . Electronics , 2022 , 11 ( 21 ): 3554 .

ZONG Zhikai , ZHA Lin , JIANG Jiande , et al . Asymmetric information distillation network for lightweight super resolution [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway, NJ, USA : IEEE , 2022 : 1248 - 1257 .

LIU Jie , ZHANG Wenjie , TANG Yuting , et al . Residual feature aggregation network for image super-resolution [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway, NJ, USA : IEEE , 2020 : 2356 - 2365 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multimodal Neural Network-Based Temperature Prediction Method for Lithium-Ion Batteries Under Mechanical Abuse Scenarios

Research on Entity Relation Extraction Method Based on Relational Prompts with Single-Module Single-Step Approach

Cross-Component Prediction for H.266/Versatile Video Coding Based on Lightweight Convolutional Neural Network

A Lightweight Multi-Modal Vehicle Trajectory Prediction Algorithm

Research on Railway Track Foreign Object Intrusion Detection Based on Multi-Scale Feature Fusion

Related Author

HUANG Xinrong

QIN Zhengpeng

LI Qian

LI Jie

LIU Hui

ZHANG Zhi

WANG Qiyuan

YIN Yujie

Related Institution

School of Energy and Electrical Engineering, Chang'an University

School of Computer Science and Technology, Harbin Institute of Technology

College of Electronic Engineering, National University of Defense Technology

School of Engineering, Royal Melbourne Institute of Technology

School of Electronic and Information, Northwestern Polytechnical University

⁰