SCIENCE@home

MePAT: Meta-Prior Aided Transformer for Adverse Weather Condition Restoration

Jianqiao Sun,Ziheng Cheng,Bo Chen,Xin Yuan,Chunhui Qu,Hongwei Liu

Published 2026 in IEEE transactions on circuits and systems for video technology (Print)

ABSTRACT

Image restoration under adverse weather conditions is critical for real-world applications. However, existing approaches mainly suffer from two fundamental limitations, i) the impractical requirement of prior degradation knowledge for task-specific model selection and ii) performance degradation when handling with in-the-wild corruptions. To address the above issues, in this paper, we propose a novel Meta-prior Aided Transformer restoration framework, MePAT, to synergize dynamic feature modulation with optimal transport (OT) theory. Specifically, we first architect an efficient attention mechanism, rectified self-channel attention (RSCA) to capture long-range associations along the channel dimension. Then, to adaptively tackle different conditions, we design a task-shared prior learning network (TPLN) to generate content-adaptive weather embeddings and serve as feature modulators to direct a more flexible and robust restoration process. In addition to learn discriminative task features, we propose an weakly-supervised OT-driven contrastive loss to measure the discrepancy between different weather corruptions. During the inference process, through the shared TPLN, we derive image-oriented vectors for unseen corruptions and then perform image restoration. The superior experimental results on three synthetic benchmarks demonstrate the effectiveness of MePAT. We also conduct experiments on real-world applications to verify the generalization ability and robustness. The code and pre-trained models will be made available.

PUBLICATION RECORD

  • Publication year

    2026

  • Venue

    IEEE transactions on circuits and systems for video technology (Print)

  • Publication date

    2026-02-01

  • Fields of study

    Computer Science, Engineering, Environmental Science

  • Identifiers
    DOI 10.1109/TCSVT.2025.3587041
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-76 of 76 references · Page 1 of 1

CITED BY