计算机科学
水下
人工智能
图像复原
任务(项目管理)
特征提取
过程(计算)
计算机视觉
排名(信息检索)
图像质量
相似性(几何)
特征(语言学)
机器学习
任务分析
编码(集合论)
图像(数学)
数据挖掘
模式识别(心理学)
培训(气象学)
质量(理念)
完备性(序理论)
相似性度量
图像处理
衰减
度量(数据仓库)
人工神经网络
可靠性(半导体)
可视化
作者
Qianying Tang,Xiaoyu Guo,Xiang Wei,Xinyu Li,Dongjin Wang,Shunli Zhang
标识
DOI:10.1109/tcsvt.2025.3620566
摘要
Underwater images, often affected by light attenuation and particle scattering, pose a challenge for restoration, aggravated by the difficulty in obtaining a substantial amount of annotated data. Existing methods have tackled this issue through the development of semi-supervised frameworks; however, they commonly lack a suitable strategy or rely on additional models trained on extra data to ensure the quality of pseudo-labels. To address this, we propose a self-assessment training framework for semi-supervised underwater image restoration (SAT-UIR). SAT-UIR employs a dual-task network (DT-Net) incorporating an auxiliary assessment task to align the restored image with a target structure similarity index measure score. This enables accurate restoration completeness estimation at a feature level and effective pseudo-label filtering during self-training. Leveraging multi-scale features, the assessment task also encourages the model to learn advantageous features for image restoration. Moreover, we integrate a soft ranking loss to further refine the training process of the auxiliary assessment task. Comprehensive experiments on various underwater benchmarks demonstrate that SAT-UIR outperforms state-of-the-art methods quantitatively and qualitatively. The code is available at https://github.com/aroid721/SAT-UIR.
科研通智能强力驱动
Strongly Powered by AbleSci AI