Empowering Semantic-Sensitive Underwater Image Enhancement with VLM

• URL: http://arxiv.org/abs/2603.12773v1
• Date: Fri, 13 Mar 2026 08:17:06 GMT
• Title: Empowering Semantic-Sensitive Underwater Image Enhancement with VLM
• Abstract summary: This work proposes a new learning mechanism to empower UIE models with semantic-sensitive capabilities.<n>To be concrete, our strategy first generates textual descriptions of key objects from a degraded image via Vision-Language Models (VLMs)<n>This map then steers the UIE network through a dual-guidance mechanism, which combines cross-attention and an explicit alignment loss.
• Score: 36.64722763619419
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, learning-based underwater image enhancement (UIE) techniques have rapidly evolved. However, distribution shifts between high-quality enhanced outputs and natural images can hinder semantic cue extraction for downstream vision tasks, thereby limiting the adaptability of existing enhancement models. To address this challenge, this work proposes a new learning mechanism that leverages Vision-Language Models (VLMs) to empower UIE models with semantic-sensitive capabilities. To be concrete, our strategy first generates textual descriptions of key objects from a degraded image via VLMs. Subsequently, a text-image alignment model remaps these relevant descriptions back onto the image to produce a spatial semantic guidance map. This map then steers the UIE network through a dual-guidance mechanism, which combines cross-attention and an explicit alignment loss. This forces the network to focus its restorative power on semantic-sensitive regions during image reconstruction, rather than pursuing a globally uniform improvement, thereby ensuring the faithful restoration of key object features. Experiments confirm that when our strategy is applied to different UIE baselines, significantly boosts their performance on perceptual quality metrics as well as enhances their performance on detection and segmentation tasks, validating its effectiveness and adaptability.

Related papers

• Large AI Model-Enabled Generative Semantic Communications for Image Transmission [37.127618237197495]
  We introduce an innovative generative semantic communication system that refines semantic granularity by segmenting images into key and non-key regions.<n>Key regions, which contain essential visual information, are processed using an image oriented semantic encoder.<n>Non-key regions are efficiently compressed through an image-to-text modeling approach.
  arXiv  Detail & Related papers  (2025-09-24T07:46:38Z)
• GCRPNet: Graph-Enhanced Contextual and Regional Perception Network for Salient Object Detection in Optical Remote Sensing Images [68.33481681452675]
  We propose a graph-enhanced contextual and regional perception network (GCRPNet)<n>It builds upon the Mamba architecture to simultaneously capture long-range dependencies and enhance regional feature representation.<n>It performs adaptive patch scanning on feature maps processed via multi-scale convolutions, thereby capturing rich local region information.
  arXiv  Detail & Related papers  (2025-08-14T11:31:43Z)
• Underlying Semantic Diffusion for Effective and Efficient In-Context Learning [113.4003355229632]
  Underlying Semantic Diffusion (US-Diffusion) is an enhanced diffusion model that boosts underlying semantics learning, computational efficiency, and in-context learning capabilities.<n>We present a Feedback-Aided Learning (FAL) framework, which leverages feedback signals to guide the model in capturing semantic details.<n>We also propose a plug-and-play Efficient Sampling Strategy (ESS) for dense sampling at time steps with high-noise levels.
  arXiv  Detail & Related papers  (2025-03-06T03:06:22Z)
• Multi-Head Attention Driven Dynamic Visual-Semantic Embedding for Enhanced Image-Text Matching [0.8611782340880084]
  This study proposes an innovative visual semantic embedding model, Multi-Headed Consensus-Aware Visual-Semantic Embedding (MH-CVSE)<n>This model introduces a multi-head self-attention mechanism based on the consensus-aware visual semantic embedding model (CVSE) to capture information in multiple subspaces in parallel.<n>In terms of loss function design, the MH-CVSE model adopts a dynamic weight adjustment strategy to dynamically adjust the weight according to the loss value itself.
  arXiv  Detail & Related papers  (2024-12-26T11:46:22Z)
• 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)
• Locality Alignment Improves Vision-Language Models [55.275235524659905]
  Vision language models (VLMs) have seen growing adoption in recent years, but many still struggle with basic spatial reasoning errors.<n>Our goal is to resolve this with a vision backbone that effectively captures both local and global image semantics.<n>We propose a new efficient post-training stage for ViTs called locality alignment and a novel fine-tuning procedure called MaskEmbed.
  arXiv  Detail & Related papers  (2024-10-14T21:01:01Z)
• Fiducial Focus Augmentation for Facial Landmark Detection [4.433764381081446]
  We propose a novel image augmentation technique to enhance the model's understanding of facial structures. We employ a Siamese architecture-based training mechanism with a Deep Canonical Correlation Analysis (DCCA)-based loss. Our approach outperforms multiple state-of-the-art approaches across various benchmark datasets.
  arXiv  Detail & Related papers  (2024-02-23T01:34:00Z)
• 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)
• Learning Image Deraining Transformer Network with Dynamic Dual Self-Attention [46.11162082219387]
  This paper proposes an effective image deraining Transformer with dynamic dual self-attention (DDSA) Specifically, we only select the most useful similarity values based on top-k approximate calculation to achieve sparse attention. In addition, we also develop a novel spatial-enhanced feed-forward network (SEFN) to further obtain a more accurate representation for achieving high-quality derained results.
  arXiv  Detail & Related papers  (2023-08-15T13:59:47Z)
• 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)
• Semantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement [58.075720488942125]
  Underwater image enhancement has become an attractive topic as a significant technology in marine engineering and aquatic robotics. We develop an efficient and compact enhancement network in collaboration with a high-level semantic-aware pretrained model. We also apply the proposed algorithm to the underwater salient object detection task to reveal the favorable semantic-aware ability for high-level vision tasks.
  arXiv  Detail & Related papers  (2022-11-19T07:50:34Z)

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.