App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 4

Super resolution reconstruction network based on multi-scale large kernel convolution and improved nonlocal attention

Li Jinfeng1
Wang Shiyu2,3
Bian Jilong2
1. College of Computer & Information Technology, Mudanjiang Normal University, Mudanjiang Heilongjiang 157011, China
2. College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China
3. Yantai Port Co, Ltd, Unicom International General Cargo Terminal Branch, Yantai Shandong 264001, China
DOI: 10.19734/j.issn.1001-3695.2025.07.0290

Abstract

In deep learning–based image super-resolution (SR) tasks, convolutional neural networks (CNNs) have long dominated the field. However, CNNs suffer from an inherent limitation in their restricted receptive fields. Motivated by their remarkable success in natural language processing, Transformers were subsequently introduced into SR. The self-attention mechanism effectively alleviates the locality constraints of convolution operations, but it faces challenges of quadratic computational complexity and excessive memory overhead when processing high-resolution images. To address these issues, this paper proposes a super resolution reconstruction network based on multi-scale large kernel convolution and improved nonlocal attention. The network adopts multi-scale large-kernel convolution blocks as its backbone and introduces a large-kernel separable attention block to replace the final convolution layer in the feature extraction network. In addition, we replace the traditional Softmax transformation with a soft-thresholding operation and incorporate SB-LSH preprocessing to enhance non-local attention. Experimental results demonstrate that our model achieves significant improvements over other state-of-the-art methods across multiple evaluation metrics. At the same time, it maintains a moderate number of parameters, avoids excessive computational costs, and produces visually realistic image reconstruction results.

Foundation Support

黑龙江省高校基本科研业务费项目(1454YB015)
黑龙江省自然科学基金资助项目(PL2024F023)
牡丹江师范学院项目(MNUGP202304)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.07.0290
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 4

Publish History

[2025-12-12] Accepted Paper

Cite This Article

李金凤, 王世宇, 边继龙. 基于多尺度大核卷积和改进非局部注意力的超分辨率重建网络 [J]. 计算机应用研究, 2026, 43 (4). (2025-12-19). https://doi.org/10.19734/j.issn.1001-3695.2025.07.0290. (Li Jinfeng, Wang Shiyu, Bian Jilong. Super resolution reconstruction network based on multi-scale large kernel convolution and improved nonlocal attention [J]. Application Research of Computers, 2026, 43 (4). (2025-12-19). https://doi.org/10.19734/j.issn.1001-3695.2025.07.0290. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)