Degradation-Aware Prompt Learning With Cross-Modal Compensation for Adverse Weather Removal
IEEE Transactions on Image Processing · 2026 · 35 · 8370-8385
DOI: 10.1109/tip.2026.3715751 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Wanshu Fan und 7 weiteren Autor:innen. Die Arbeit nennt 79 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Liaoning Provincial Key Research and Development Joint Program, Educational Department of Liaoning Province.
Abstract (Originalsprache)
Adverse weather causes diverse and complex image degradations, severely compromising the reliability of computer vision systems. Existing all-in-one restoration models attempt to address multiple degradation types within a unified framework, but often lack explicit spatial and semantic modeling of degradation characteristics, limiting their adaptability to diverse weather conditions. To address this limitation, we propose a Degradation-Aware Cross-Modal Prompt Compensation Network (DCMPC-Net) that leverages cross-modal degradation cues from a pre-trained vision-language model to condition restoration features within a unified backbone. Specifically, our DCMPC-Net mainly consists of the Cross-Modal Prompt Generator (CMPG), Prompt-Guided Attention Alignment Module (PGAAM), and Dual Feature Compensation Module (DFCM). The CMPG integrates textual embeddings with visual features to produce degradation-aware prompts that encode degradation-related semantic and contextual cues. These prompts are injected into the decoder via a PGAAM, which adaptively aligns semantic information with degraded regions to facilitate context-aware restoration. To further enhance structural fidelity, DFCM is introduced that disentangles degradation artifacts from scene structures, thereby improving the reconstruction of fine textures and detailed content. By integrating cross-modal semantic guidance with spatial alignment and structural enhancement, DCMPC-Net achieves robust and perceptually consistent restoration across diverse weather conditions. Extensive experiments show that DCMPC-Net outperforms state-of-the-art methods in both task-specific and unified settings, achieving superior accuracy and visual fidelity. The code is available at https://github.com/fanamber831/DCMPC-Net.
Förderung
- National Natural Science Foundation of China
- Liaoning Provincial Key Research and Development Joint Program
- Educational Department of Liaoning Province
- Interdisciplinary Project of Dalian University
- 111 Center
Zitieren
APA
Fan, W., Zhang, Y., Shen, Y., Wang, L., Qin, J., Lam, K. M., Wang, C., & Pan, J. (2026). Degradation-Aware Prompt Learning With Cross-Modal Compensation for Adverse Weather Removal. IEEE Transactions on Image Processing, 35, 8370-8385. https://doi.org/10.1109/tip.2026.3715751
Vancouver
Fan W, Zhang Y, Shen Y, Wang L, Qin J, Lam KM, et al. Degradation-Aware Prompt Learning With Cross-Modal Compensation for Adverse Weather Removal. IEEE Transactions on Image Processing. 2026;35:8370-8385. doi:10.1109/tip.2026.3715751
BibTeX
@article{Fan2026,
author = {Fan, Wanshu and Zhang, Yunzhe and Shen, Yue and Wang, Liyan and Qin, Jing and Lam, Kin-Man and Wang, Cong and Pan, Jinshan},
title = {Degradation-Aware Prompt Learning With Cross-Modal Compensation for Adverse Weather Removal},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {8370--8385},
doi = {10.1109/tip.2026.3715751}
}
EUVIMED