EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semi-Supervised Degradation-Aware Learning for All-in-One Weather-Degraded Image Restoration

Lei Cai, Fang Ruan, Wei Lu, Qi Lin, Huijie Zheng, Wenjie Xiang, Tao Zhu

Electronics · 17.06.2026 · 15 (12) · 2686

DOI: 10.3390/electronics15122686 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 17.06.2026. Verfasst von Lei Cai und 6 weiteren Autor:innen. Die Arbeit nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Natural Science Foundation of Xiamen, Natural Science Foundation of Fujian Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

All-in-one weather-degraded image restoration aims to restore clean images from diverse weather-degraded observations (such as rain, haze, and snow) using a unified model. However, this topic remains challenging due to its ill-posed nature and the scarcity of large-scale paired training data. This article develops a novel semi-supervised learning framework, termed Semi-Supervised Degradation-Aware Learning (S2DAL), to adjust the feature space to align with the unified parameter space for all-in-one adverse weather removal. Specifically, the proposed S2DAL consists of two backbone networks: a Degradation-guided Histogram Transformer (DHformer) for weather-degraded image restoration and a Degradation-guided Convolutional Neural Network (DCNN) for degradation generation. A key component, the Degradation-guided Histogram Transformer (DHT) block, is designed to effectively capture intrinsic image features while suppressing diverse degradation interference through channel shuffling modulation, dynamic-range histogram self-attention, and dual-scale gated feed forward. Furthermore, a Monte Carlo-based Expectation-Maximization (EM) algorithm is introduced to jointly optimize latent variables and network parameters under both labeled and unlabeled data. Extensive quantitative and qualitative results on synthetic and real-world datasets consistently demonstrate that the proposed S2DAL achieves superior restoration performance compared to multiple state-of-the-art fully supervised and semi-supervised approaches.

Förderung

  • National Key R&D Program of China
  • Natural Science Foundation of Xiamen
  • Natural Science Foundation of Fujian Province
  • Huaqiao University Research Startup Funds
  • Open List and Leader Appointment Project of Fujian Province
  • Key Project of Natural Science Foundation of Fujian Province
  • Key Science and Technology Project of Xiamen City
  • High-level Talent Team Project of Quanzhou City

Zitieren

APA

Cai, L., Ruan, F., Lu, W., Lin, Q., Zheng, H., Xiang, W., & Zhu, T. (2026). Semi-Supervised Degradation-Aware Learning for All-in-One Weather-Degraded Image Restoration. Electronics, 15(12), 2686. https://doi.org/10.3390/electronics15122686

Vancouver

Cai L, Ruan F, Lu W, Lin Q, Zheng H, Xiang W, et al. Semi-Supervised Degradation-Aware Learning for All-in-One Weather-Degraded Image Restoration. Electronics. 2026;15(12):2686. doi:10.3390/electronics15122686

BibTeX
@article{Cai2026,
  author = {Cai, Lei and Ruan, Fang and Lu, Wei and Lin, Qi and Zheng, Huijie and Xiang, Wenjie and Zhu, Tao},
  title = {Semi-Supervised Degradation-Aware Learning for All-in-One Weather-Degraded Image Restoration},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {12},
  pages = {2686},
  doi = {10.3390/electronics15122686}
}
Kostenlos starten →