AI News HubLIVE
Original source2 min read

VLMs Win a Systematic Evaluation of Underwater Image Reconstruction

arXiv:2608.11425v1 Announce Type: new Abstract: Underwater image restoration consists of recovering an image which looks like there is no water present. To date, evaluation has not been systematic. This paper describes a systematic evaluation pipeline for underwater reconstruction, which can be used to assess a method for accuracy; consistency of reconstruction over camera moves; and the effect of water parameters. We use this pipeline to evaluate a range of current procedures, from models constructed using explicit but approximate physical models of scattering to Vision-Language Models (VLMs which are not currently trained with explicit physical models). Overall, VLMs wholly and significantly outperform physically based models in our evaluation, likely because of the importance of a strong image prior. Results on images of real underwater scenes strongly confirm the evaluation.

SourcearXiv Computer VisionAuthor: Sara Aghajanzadeh, Yingxue Wang, Ieva Bagdonaviciute, David Forsyth

-->

[Submitted on 11 Aug 2026]

Title:VLMs Win a Systematic Evaluation of Underwater Image Reconstruction

View a PDF of the paper titled VLMs Win a Systematic Evaluation of Underwater Image Reconstruction, by Sara Aghajanzadeh and Yingxue Wang and Ieva Bagdonaviciute and David Forsyth

View PDF HTML (experimental)

Abstract:Underwater image restoration consists of recovering an image which looks like there is no water present. To date, evaluation has not been systematic. This paper describes a systematic evaluation pipeline for underwater reconstruction, which can be used to assess a method for accuracy; consistency of reconstruction over camera moves; and the effect of water parameters. We use this pipeline to evaluate a range of current procedures, from models constructed using explicit but approximate physical models of scattering to Vision-Language Models (VLMs which are not currently trained with explicit physical models). Overall, VLMs wholly and significantly outperform physically based models in our evaluation, likely because of the importance of a strong image prior. Results on images of real underwater scenes strongly confirm the evaluation.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2608.11425 [cs.CV]

(or arXiv:2608.11425v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2608.11425

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Sara Aghajanzadeh [view email] [v1] Tue, 11 Aug 2026 20:46:46 UTC (44,190 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled VLMs Win a Systematic Evaluation of Underwater Image Reconstruction, by Sara Aghajanzadeh and Yingxue Wang and Ieva Bagdonaviciute and David Forsyth

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-08

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)