Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Design

• URL: http://arxiv.org/abs/2603.01767v1
• Date: Mon, 02 Mar 2026 11:50:09 GMT
• Title: Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Design
• Authors: Bosen Lin, Feng Gao, Yanwei Yu, Junyu Dong, Qian Du,
• Abstract summary: 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.
• Score: 53.9340120911759
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In real underwater environments, downstream image recognition tasks such as semantic segmentation and object detection often face challenges posed by problems like blurring and color inconsistencies. Underwater image enhancement (UIE) has emerged as a promising preprocessing approach, aiming to improve the recognizability of targets in underwater images. However, most existing UIE methods mainly focus on enhancing images for human visual perception, frequently failing to reconstruct high-frequency details that are critical for task-specific recognition. To address this issue, we propose a Downstream Task-Inspired Underwater Image Enhancement (DTI-UIE) framework, which leverages human visual perception model to enhance images effectively for underwater vision tasks. Specifically, we design an efficient two-branch network with task-aware attention module for feature mixing. The network benefits from a multi-stage training framework and a task-driven perceptual loss. Additionally, inspired by human perception, we automatically construct a Task-Inspired UIE Dataset (TI-UIED) using various task-specific networks. Experimental results demonstrate that DTI-UIE significantly improves task performance by generating preprocessed images that are beneficial for downstream tasks such as semantic segmentation, object detection, and instance segmentation. The codes are publicly available at https://github.com/oucailab/DTIUIE.

Related papers

• VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning [68.98988753763666]
  We propose VisualCloze, a universal image generation framework.<n>VisualCloze supports a wide range of in-domain tasks, generalization to unseen ones, unseen unification of multiple tasks, and reverse generation.<n>We introduce Graph200K, a graph-structured dataset that establishes various interrelated tasks, enhancing task density and transferable knowledge.
  arXiv  Detail & Related papers  (2025-04-10T17:59:42Z)
• 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)
• FriendNet: Detection-Friendly Dehazing Network [24.372610892854283]
  We propose an effective architecture that bridges image dehazing and object detection together via guidance information and task-driven learning.<n>FriendNet aims to deliver both high-quality perception and high detection capacity.
  arXiv  Detail & Related papers  (2024-03-07T12:19:04Z)
• Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving [85.62076860189116]
  Video Task Decathlon (VTD) includes ten representative image and video tasks spanning classification, segmentation, localization, and association of objects and pixels. We develop our unified network, VTDNet, that uses a single structure and a single set of weights for all ten tasks.
  arXiv  Detail & Related papers  (2023-09-08T16:33:27Z)
• Joint Perceptual Learning for Enhancement and Object Detection in Underwater Scenarios [41.34564703212461]
  We propose a bilevel optimization formulation for jointly learning underwater object detection and image enhancement. Our method outputs visually favoring images and higher detection accuracy.
  arXiv  Detail & Related papers  (2023-07-07T11:54:06Z)
• 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)
• A Benchmark dataset for both underwater image enhancement and underwater object detection [34.25890702670983]
  We provide a large-scale underwater object detection dataset with both bounding box annotations and high quality reference images. The OUC dataset provides a platform to comprehensive study the influence of underwater image enhancement algorithms on the underwater object detection task.
  arXiv  Detail & Related papers  (2020-06-29T03:12:50Z)

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.