# Unveiling the Underwater World: CLIP Perception Model-Guided Underwater Image Enhancement

arXiv: https://arxiv.org/abs/2507.06234 · HTML: https://mlsanity.com/paper/2507.06234/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 29 Apr 2025.

## Builds on (most cited first, 17 of 17)

- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [U-shape Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2111.11843/) (2021)
- [Underwater Ranker: Learn Which Is Better and How to Be Better](https://mlsanity.com/paper/2208.06857/) (2022)
- [Uncertainty Inspired Underwater Image Enhancement](https://mlsanity.com/paper/2207.09689/) (2022)
- [PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators](https://mlsanity.com/paper/2306.08918/) (2023)
- [Shallow-UWnet : Compressed Model for Underwater Image Enhancement](https://mlsanity.com/paper/2101.02073/) (2021)
- [Diving Deeper into Underwater Image Enhancement: A Survey](https://mlsanity.com/paper/1907.07863/) (2019)
- [SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots](https://mlsanity.com/paper/2011.06252/) (2020)
- [Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Image](https://mlsanity.com/paper/1909.11983/) (2019)
- [Underwater Image Restoration via Contrastive Learning and a Real-world Dataset](https://mlsanity.com/paper/2106.10718/) (2021)
- [Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2204.11018/) (2022)
- [UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detection](https://mlsanity.com/paper/2309.04708/) (2023)
- [MirrorDiffusion: Stabilizing Diffusion Process in Zero-shot Image Translation by Prompts Redescription and Beyond](https://mlsanity.com/paper/2401.03221/) (2024)

## Built on by (most cited first, 2 of 2)

- [Fusing Transferred Priors and Physics-based Decomposition for Underwater Image Enhancement](https://mlsanity.com/paper/2606.15648/) (2026)
- [PolUR: Polarization Aware Multimodal Degradation Perception for Underwater Image Restoration](https://mlsanity.com/paper/2610.17991/) (2026)

## Abstract (arXiv)

High-quality underwater images are essential for both machine vision tasks and viewers with their aesthetic appeal.However, the quality of underwater images is severely affected by light absorption and scattering. Deep learning-based methods for Underwater Image Enhancement (UIE) have achieved good performance. However, these methods often overlook considering human perception and lack sufficient constraints within the solution space. Consequently, the enhanced images often suffer from diminished perceptual quality or poor content restoration.To address these issues, we propose a UIE method with a Contrastive Language-Image Pre-Training (CLIP) perception loss module and curriculum contrastive regularization. Above all, to develop a perception model for underwater images that more aligns with human visual perception, the visual semantic feature extraction capability of the CLIP model is leveraged to learn an appropriate prompt pair to map and evaluate the quality of underwater images. This CLIP perception model is then incorporated as a perception loss module into the enhancement network to improve the perceptual quality of enhanced images. Furthermore, the CLIP perception model is integrated with the curriculum contrastive regularization to enhance the constraints imposed on the enhanced images within the CLIP perceptual space, mitigating the risk of both under-enhancement and over-enhancement. Specifically, the CLIP perception model is employed to assess and categorize the learning difficulty level of negatives in the regularization process, ensuring comprehensive and nuanced utilization of distorted images and negatives with varied quality levels. Extensive experiments demonstrate that our method outperforms state-of-the-art methods in terms of visual quality and generalization ability.