App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 11

Dual guidance-based prompt-driven all-in-one image restoration

Ma Zongfang1,2
Guo Da1,2
Zhang Guofei1,2
Song Lin1,2
1. State Key Laboratory of Green Building in Western China, Xian Shanxi 710055, China
2. College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xian Shanxi 710055, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0087

Abstract

Integrated image restoration addresses various degradation issues, such as defogging and rain removal, using a single model. However, existing methods lack explicit external guidance. This limitation makes it difficult to handle complex or mixed degradation scenarios. To address above issues, this paper proposed a prompt-driven general-purpose image restoration network, The network focused on a dual global-local guidance mechanism combining prior knowledge and structure SPG-DGL. At the prior level, decoupled prompt learning generated degradation-aware global and multi-scale local prompts, ensured structural integrity and fine-texture recovery respectively; at the structural level, this study constructed a hybrid backbone combining CNNs and Transformers. To enhance long-range modelling capabilities, this research designed an Efficient Large-Kernel Decomposition (ELKD) module that transforms large kernels into small, hardware-friendly ones. It successfully expanded the receptive field whilst improving throughput. Experiments demonstrate that this method significantly outperforms existing state-of-the-art methods across multiple degradation tasks. It effectively achieves an optimal balance between global structure and local fine-texture recovery, providing a highly generalizable and inference-efficient solution for complex degradation scenarios.

Foundation Support

国家自然科学基金资助项目(62276207)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0087
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 11

Publish History

[2026-07-17] Accepted Paper

Cite This Article

马宗方, 郭达, 张国飞, 等. 基于双重全局-局部引导的提示驱动一体化图像恢复模型 [J]. 计算机应用研究, 2026, 43 (11). (2026-07-31). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0087. (Ma Zongfang, Guo Da, Zhang Guofei, et al. Dual guidance-based prompt-driven all-in-one image restoration [J]. Application Research of Computers, 2026, 43 (11). (2026-07-31). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0087. )

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)