Fusing Transferred Priors and Physics-based Decomposition for Underwater Image Enhancement

• URL: http://arxiv.org/abs/2606.15648v1
• Date: Sun, 14 Jun 2026 07:39:32 GMT
• Title: Fusing Transferred Priors and Physics-based Decomposition for Underwater Image Enhancement
• Abstract summary: We propose a transfer learning-based UIE that does not require underwater images to have paired noisy or true labels for learning.<n>A novel UIE is available via transfer learning, and the physics-aligned UIE decomposition provides theoretical soundness.
• Score: 11.996160498403427
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The underwater images are captured within diverse water-medium conditions, leading to complex degradation, including color bias, low contrast, and blur effect. Recently, learning-based methods have demonstrated their potential for underwater image enhancement (UIE). However, most of the previous work focus on the training strategy or network design to make the enhanced result aligned well with the labels in datasets, ignoring that the labels are selected from the enhanced results of previous UIE methods and these pseudo-labels are noisy. Consequently, the performance of their models is not satisfactory to a certain extent. However, collecting the true labels of the underwater images is challenging. In this work, we propose a transfer learning-based UIE that does not require underwater images to have paired noisy or true labels for learning. Instead, the UIE task is first divided into global color correction, haze removal, and background noise suppression following the underwater physics. Then multiple types of prior from other vision tasks are leveraged as cross-domain supervision in each step. In this way, a novel UIE is available via transfer learning, and the physics-aligned UIE decomposition provides theoretical soundness. Qualitative and quantitative experiments demonstrate that our proposal based on physics and priors fusion achieves SOTA performance in the UIE task and effectively boosts downstream vision tasks, significantly outperforming benchmark methods. Project repo: https://github.com/Haru2022/P2-UIE.

Related papers

• Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Design [53.9340120911759]
  We propose a Downstream Task-Inspired Underwater Image Enhancement (DTI-UIE) framework to enhance images effectively for underwater vision tasks.<n>Specifically, we design an efficient two-branch network with task-aware attention module for feature mixing.<n>We show that DTI-UIE significantly improves task performance by generating preprocessed images that are beneficial for downstream tasks.
  arXiv  Detail & Related papers  (2026-03-02T11:50:09Z)
• HUPE: Heuristic Underwater Perceptual Enhancement with Semantic Collaborative Learning [62.264673293638175]
  Existing underwater image enhancement methods primarily focus on improving visual quality while overlooking practical implications.<n>We propose a invertible network for underwater perception enhancement, dubbed H, which enhances visual quality and demonstrates flexibility in handling other downstream tasks.
  arXiv  Detail & Related papers  (2024-11-27T12:37:03Z)
• Underwater Image Enhancement with Cascaded Contrastive Learning [51.897854142606725]
  Underwater image enhancement (UIE) is a highly challenging task due to the complexity of underwater environment and the diversity of underwater image degradation. Most of the existing deep learning-based UIE methods follow a single-stage network which cannot effectively address the diverse degradations simultaneously. We propose a two-stage deep learning framework and taking advantage of cascaded contrastive learning to guide the network training of each stage.
  arXiv  Detail & Related papers  (2024-11-16T03:16:44Z)
• UIE-UnFold: Deep Unfolding Network with Color Priors and Vision Transformer for Underwater Image Enhancement [27.535028176427623]
  Underwater image enhancement (UIE) plays a crucial role in various marine applications. Current learning-based approaches frequently lack explicit prior knowledge about the physical processes involved in underwater image formation. This paper proposes a novel deep unfolding network (DUN) for UIE that integrates color priors and inter-stage feature incorporation.
  arXiv  Detail & Related papers  (2024-08-20T08:48:33Z)
• DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image Enhancement [77.0360085530701]
  Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments. Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features. Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
  arXiv  Detail & Related papers  (2023-12-12T06:07:21Z)
• UIEDP:Underwater Image Enhancement with Diffusion Prior [20.349103580702028]
  Underwater image enhancement (UIE) aims to generate clear images from low-quality underwater images. We propose UIEDP, a novel framework treating UIE as a posterior distribution sampling process of clear images conditioned on degraded underwater inputs.
  arXiv  Detail & Related papers  (2023-12-11T09:24:52Z)
• RAUNE-Net: A Residual and Attention-Driven Underwater Image Enhancement Method [2.6645441842326756]
  Underwater image enhancement (UIE) poses challenges due to distinctive properties of the underwater environment. In this paper, we propose a more reliable and reasonable UIE network called RAUNE-Net. Our method obtains promising objective performance and consistent visual results across various real-world underwater images.
  arXiv  Detail & Related papers  (2023-11-01T03:00:07Z)
• Learning Heavily-Degraded Prior for Underwater Object Detection [59.5084433933765]
  This paper seeks transferable prior knowledge from detector-friendly images. It is based on statistical observations that, the heavily degraded regions of detector-friendly (DFUI) and underwater images have evident feature distribution gaps. Our method with higher speeds and less parameters still performs better than transformer-based detectors.
  arXiv  Detail & Related papers  (2023-08-24T12:32:46Z)
• Semi-supervised Underwater Image Enhancement Using A Physics-Aware Triple-Stream Network [6.7932860553262415]
  We leverage both the physics-based Image Formation Model (IFM) and deep learning techniques for Underwater Image Enhancement (UIE)<n> PATS-UIENet comprises a Direct Signal Transmission Estimation Steam (D-Stream), a Backscatter Signal Transmission Estimation Steam (B-Stream) and an Ambient Light Estimation Stream (A-Stream)<n>We also adopt an IFM-inspired semi-supervised learning framework, which exploits both the labeled and unlabeled images, to address the issue of insufficient data.
  arXiv  Detail & Related papers  (2023-07-21T10:10:18Z)
• PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators [120.06891448820447]
  How to obtain clear and visually pleasant images has become a common concern of people. The task of underwater image enhancement (UIE) has also emerged as the times require. In this paper, we propose a physical model-guided GAN model for UIE, referred to as PUGAN. Our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics.
  arXiv  Detail & Related papers  (2023-06-15T07:41:12Z)
• SyreaNet: A Physically Guided Underwater Image Enhancement Framework Integrating Synthetic and Real Images [17.471353846746474]
  Underwater image enhancement (UIE) is vital for high-level vision-related underwater tasks. We propose a framework textitSyreaNet for UIE that integrates both synthetic and real data.
  arXiv  Detail & Related papers  (2023-02-16T12:57:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.