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

TL;DR

This work proposes a Downstream Task-Inspired Underwater Image Enhancement (DTI-UIE) framework, which leverages human visual perception model to enhance images effectively for underwater vision tasks, and designs an efficient two-branch network with task-aware attention module for feature mixing.

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.

Figures (11)

• Figure 1: Framework of the proposed DTI-UIE. (a) A task-inspired UIE dataset is constructed automatically by task networks. (b) A UIE network providing advantages for downstream tasks is achieved with task-relevant priors and task-driven perceptual loss.
• Figure 2: Underwater images enhanced using different UIE methods. UColor liUnderwaterImageEnhancement2021 and HUPEzhangHUPEHeuristicUnderwater2025 blurred the outlines of the diver and background, and introduced additional edge and texture information to the foreground seabed. The proposed DTI-UIE introduced more accurate foreground-background differentiation and reduced texture and edge noise, which is beneficial for downstream tasks.
• Figure 3: (a) The percentage of images from different UIE sources corresponding to ground truth in the entire TI-UIED dataset. (b) Number of images containing each object category.
• Figure 4: Example raw and references images in the TI-UIED dataset.
• Figure 5: Overview of the proposed DTI-UIE framework, which consists of the enhancement network $\mathbf{Enc}$ and two task network $\mathbf{Seg}_{pri}$, $\mathbf{Seg}_{task}$. In the first stage, the task network $\mathbf{Seg}_{pri}$ for task-relevant prior is trained. During the second stage, DTI-UIE updates the enhancement network $\mathbf{Enc}$ using the TDP loss and pixel loss, while both two task networks are frozen. In the third stage, the task network $\mathbf{Seg}_{task}$ for TDP loss is updated, using different kinds of enhanced and mixed images.