Metraipolis › archive › dc_067f6442fdf3

Zero-Shot Benchmarking of Unified Multimodal Models for Shallow-Water UAV Image Distortion Assessment and Restoration — arXiv:2611.09740

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09740
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:28.218Z
SHA-256 of the archived text
5cb632b5038353b945b1d9ddd38eb3395dae437b0f8dfe18f0b48de54ce02e9d
Stable URL of this page
https://metraipolis.com/documento/dc_067f6442fdf3

How to cite

Zero-Shot Benchmarking of Unified Multimodal Models for Shallow-Water UAV Image Distortion Assessment and Restoration — arXiv:2611.09740 — arXiv (en), https://arxiv.org/abs/2611.09740 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_067f6442fdf3 (Metraipolis archive dc_067f6442fdf3, sha256 5cb632b5038353b945b1d9ddd38eb3395dae437b0f8dfe18f0b48de54ce02e9d)
BibTeX
@misc{dc067f6442fdf3,
  title = {Zero-Shot Benchmarking of Unified Multimodal Models for Shallow-Water UAV Image Distortion Assessment and Restoration — arXiv:2611.09740},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09740},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_067f6442fdf3; sha256 5cb632b5038353b945b1d9ddd38eb3395dae437b0f8dfe18f0b48de54ce02e9d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09740. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Shallow-water UAV imagery provides centimeter-scale observations of benthic environments, but water-induced distortions complicate interpretation. To our knowledge, we present the first systematic zero-shot benchmark of unified multimodal large language models (MLLMs) for both assessing water-induced distortions and restoring shallow-water imagery within the same model framework. We evaluate five open-weight unified MLLMs with frozen pretrained weights and without access to paired reference images or descriptions of the true seabed. The benchmark contains 1,000 image pairs: 600 semi-synthetic UAV scenes created by applying synthetic water distortions to real shallow-water imagery and 400 fully synthetic through-water scenes. Three independent human annotations cover five distortion types. We evaluate four assessment prompts (P0-P3), from direct instruction to structured task decomposition, on all 1,000 images and four diagnosis-guided restoration prompts (R0-R3) on a common 100-image subset. Assessment varies substantially by model and prompt, with systematic prediction biases and a best pooled balanced accuracy of 0.654 for distortion presence. The best pooled PSNR gain is +0.255 dB, no unified MLLM improves pooled LPIPS, and some outputs alter scene structure or hallucinate content. Two restoration-only baselines also show limited transfer: InstructIR achieves a pooled PSNR gain of +0.040 dB, while PromptFix degrades all four pooled metrics under every prompt. These results show that recognizing shallow-water degradation does not imply reliable physical restoration and provide a reproducible baseline for future work.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.09740 — 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 2026-11-09T22:37:47.234Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).