EUVIMEDEUVIMED entdecken
Crossref

Empowering Semantic-Sensitive Underwater Image Enhancement with VLM

Guodong Fan, Shengning Zhou, Genji Yuan, Huiyu Li, Jingchun Zhou, Jinjiang Li

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3759-3767

DOI: 10.1609/aaai.v40i5.37376 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Guodong Fan und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, learning-based underwater image enhancement (UIE) techniques have rapidly evolved. However, distribution shifts between high-quality enhanced outputs and natural images can hinder semantic cue extraction for downstream vision tasks, thereby limiting the adaptability of existing enhancement models. To address this challenge, this work proposes a new learning mechanism that leverages Vision-Language Models (VLMs) to empower UIE models with semantic-sensitive capabilities. To be concrete, our strategy first generates textual descriptions of key objects from a degraded image via a VLM. Subsequently, a text-image alignment model remaps these relevant descriptions back onto the image to produce a spatial semantic guidance map. This map then steers the UIE network through a dual-guidance mechanism, which combines cross-attention and an explicit alignment loss. This forces the network to focus its restorative power on semantic-sensitive regions during image reconstruction, rather than pursuing a globally uniform improvement, thereby ensuring the faithful restoration of key object features. Experiments confirm that when our strategy is applied to different UIE baselines, significantly boosts their performance on perceptual quality metrics as well as enhances their performance on detection and segmentation tasks, validating its effectiveness and adaptability.

Zitieren

APA

Fan, G., Zhou, S., Yuan, G., Li, H., Zhou, J., & Li, J. (2026). Empowering Semantic-Sensitive Underwater Image Enhancement with VLM. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3759-3767. https://doi.org/10.1609/aaai.v40i5.37376

Vancouver

Fan G, Zhou S, Yuan G, Li H, Zhou J, Li J. Empowering Semantic-Sensitive Underwater Image Enhancement with VLM. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3759-3767. doi:10.1609/aaai.v40i5.37376

BibTeX
@article{Fan2026,
  author = {Fan, Guodong and Zhou, Shengning and Yuan, Genji and Li, Huiyu and Zhou, Jingchun and Li, Jinjiang},
  title = {Empowering Semantic-Sensitive Underwater Image Enhancement with VLM},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {3759--3767},
  doi = {10.1609/aaai.v40i5.37376}
}
Kostenlos starten →