Metraipolis › archive › dc_ec2aec7b5d6b

Learning from Failure: Leveraging Unreliable Predictions in Semi-Supervised Real-World Adverse Weather Removal — arXiv:2610.02051

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.02051
License (as archived)
CC0-1.0
Archived
2026-10-06T19:15:29.591Z
SHA-256 of the archived text
f53ee3a71d6c0829ffc9903dc2808dd935a0e2940ed07efe44817c131418b19c
Stable URL of this page
https://metraipolis.com/documento/dc_ec2aec7b5d6b

How to cite

Learning from Failure: Leveraging Unreliable Predictions in Semi-Supervised Real-World Adverse Weather Removal — arXiv:2610.02051 — arXiv (en), https://arxiv.org/abs/2610.02051 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec2aec7b5d6b (Metraipolis archive dc_ec2aec7b5d6b, sha256 f53ee3a71d6c0829ffc9903dc2808dd935a0e2940ed07efe44817c131418b19c)
BibTeX
@misc{dcec2aec7b5d6b,
  title = {Learning from Failure: Leveraging Unreliable Predictions in Semi-Supervised Real-World Adverse Weather Removal — arXiv:2610.02051},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.02051},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec2aec7b5d6b; sha256 f53ee3a71d6c0829ffc9903dc2808dd935a0e2940ed07efe44817c131418b19c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02051. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Adverse weather image restoration aims to recover images degraded by rain, haze, snow, and other weather-induced artifacts, thereby improving the robustness of outdoor vision systems. Existing unified restoration models exhibit limited generalization to real-world scenes due to their reliance on synthetic supervision and insufficient semantic constraints. In this paper, we propose a novel student--teacher semi-supervised framework that addresses both challenges. Specifically, we introduce an unreliable database that preserves failed teacher predictions as informative negative samples for contrastive learning, while a reliable database stores high-quality teacher predictions as positive samples. By jointly exploiting reliable pseudo-ground truths and unreliable teacher outputs, the proposed framework learns to enhance desirable restoration characteristics while avoiding common failures. We further propose a phase spectrum-based semantic constraint that replaces computationally expensive text-based supervision with an efficient and naturally aligned semantic prior. An adaptive phase consistency loss is also designed to dynamically balance supervision between the degraded input and teacher pseudo-ground truths according to degradation severity. Extensive experiments on real-world benchmarks demonstrate that the proposed method consistently outperforms existing state-of-the-art approaches in restoration quality and perceptual fidelity while exhibiting stronger generalization to real-world adverse weather conditions.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.02051 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T17:37:36.880Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).