EUVIMEDEUVIMED entdecken
Crossref

Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal

Rongxin Liao, Feng Li, Yanyan Wei, Zenglin Shi, Le Zhang, Huihui Bai, Meng Wang

IEEE Transactions on Image Processing · 2025 · 34 · 7422-7435

DOI: 10.1109/tip.2025.3627860 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Rongxin Liao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 108 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, National Natural Science Foundation of China, Natural Science Foundation of Anhui Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Universal adverse weather removal (UAWR) seeks to address various weather degradations within a unified framework. Recent methods are inspired by prompt learning using pre-trained vision-language models (e.g., CLIP), leveraging degradation-aware prompts to facilitate weather-free image restoration, yielding significant improvements. In this work, we propose CyclicPrompt, an innovative cyclic prompt approach designed to enhance the effectiveness, adaptability, and generalizability of UAWR. CyclicPrompt comprises two key components: 1) a composite context prompt that integrates weather-related information and context-aware representations into the network to guide restoration. This prompt differs from previous methods by marrying learnable input-conditional vectors with weather-specific knowledge, thereby improving adaptability across various degradations and 2) the erase-and-paste mechanism, after the initial guided restoration, substitutes weather-specific knowledge with constrained restoration priors, inducing high-quality weather-free concepts into the composite prompt to further fine-tune the restoration process. Therefore, we can form a cyclic "Prompt-Restore-Prompt" pipeline that adeptly harnesses weather-specific knowledge, textual contexts, and reliable textures. Extensive experiments on synthetic and real-world datasets validate the superior performance of CyclicPrompt. The code is available at: https://github.com/RongxinL/CyclicPrompt.

Förderung

  • Beijing Natural Science Foundation
  • National Natural Science Foundation of China
  • Natural Science Foundation of Anhui Province

Zitieren

APA

Liao, R., Li, F., Wei, Y., Shi, Z., Zhang, L., Bai, H., & Wang, M. (2025). Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal. IEEE Transactions on Image Processing, 34, 7422-7435. https://doi.org/10.1109/tip.2025.3627860

Vancouver

Liao R, Li F, Wei Y, Shi Z, Zhang L, Bai H, et al. Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal. IEEE Transactions on Image Processing. 2025;34:7422-7435. doi:10.1109/tip.2025.3627860

BibTeX
@article{Liao2025,
  author = {Liao, Rongxin and Li, Feng and Wei, Yanyan and Shi, Zenglin and Zhang, Le and Bai, Huihui and Wang, Meng},
  title = {Prompt to Restore, Restore to Prompt: Cyclic Prompting for Universal Adverse Weather Removal},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  volume = {34},
  pages = {7422--7435},
  doi = {10.1109/tip.2025.3627860}
}
Kostenlos starten →