Toward Efficient Underwater Visual Perception through Image Enhancement, Compression, and Understanding
Bibliographic record
Abstract
The growing demand for marine exploration, environmental monitoring, and autonomous underwater operations has elevated the role of underwater image processing in both research and practical applications. However, the acquisition and transmission of underwater visual data are fundamentally constrained by the harsh aquatic environment, where factors such as limited bandwidth, strong light scattering, color distortion, and complex noise severely degrade image quality and restrict data throughput. These challenges not only hinder real-time perception and decision-making but also affect the efficiency of data-driven tasks such as mapping, object recognition, and navigation. To address these issues, a broad spectrum of underwater image processing methods has emerged, aiming to enhance visual clarity, compress data for efficient transmission, restore degraded signals, and enable accurate scene understanding. This survey provides a structured and comprehensive review of existing techniques, categorizing them into four core domains: image enhancement, image restoration, image compression and segmentation, and image classification. Representative methods within each domain are critically analyzed in terms of their underlying principles, computational complexity, and applicability across diverse underwater scenarios. Furthermore, the survey highlights emerging trends including deep learning-based approaches, cross-modal information fusion, and resource-efficient designs, offering insights for future development in underwater visual computing and communication systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".