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 this https URL.
Abstract (translated)
在真实的水下环境中，下游图像识别任务（如语义分割和目标检测）常常会遇到诸如模糊和颜色不一致等问题所带来的挑战。水下图像增强（UIE）作为一种前景预处理方法应运而生，旨在提高水下图像中目标的可辨识性。然而，大多数现有的UIE方法主要集中在改善人类视觉感知效果上，通常无法恢复对特定任务识别至关重要的高频细节信息。为了解决这一问题，我们提出了一种受下游任务启发的水下图像增强（DTI-UIE）框架，该框架利用了人类视觉感知模型来有效提高水下视觉任务中的图像质量。具体而言，我们设计了一个高效的双分支网络，并配备了具备任务意识注意模块的功能混合结构。此外，该网络受益于一个多阶段训练框架以及一种由任务驱动的感知损失函数。另外，受人类感知启发，我们利用各种特定任务的网络自动构建了“任务启发式水下图像增强数据集”（TI-UIED）。实验结果表明，DTI-UIE通过生成有利于下游任务如语义分割、目标检测和实例分割等任务处理的预处理图像，显著提升了这些任务的表现。相关代码可以在以下链接获得：[此URL]。
URL
https://arxiv.org/abs/2603.01767
