UIERL: Internal-External Representation Learning Network for Underwater Image Enhancement

计算机科学 代表(政治) 人工智能 水下 计算机视觉 政治学 政治 海洋学 地质学 法学
作者
Zhengyong Wang,Liquan Shen,Yihan Yu,Hui Yuan
出处
期刊:IEEE Transactions on Multimedia [Institute of Electrical and Electronics Engineers]
卷期号:26: 9252-9267 被引量:20
标识
DOI:10.1109/tmm.2024.3387760
摘要

Underwater image enhancement (UIE) is a meaningful but challenging task, and many learning-based UIE methods have been proposed in recent years. Although much progress has been made, these methods still have two issues: (1) There exists a significant region-wise quality difference in a single underwater image due to the underwater imaging process, especially in regions with different scene depths. However, existing methods neglect this internal characteristic of underwater images, resulting in inferior performance; (2) Due to the uniqueness of the acquisition approach, underwater image acquisition tools usually capture multiple images in the same or similar scenes. Thus, the underwater images to be enhanced in practical usage are highly correlated. However, when processing a single image, existing methods do not consider the rich external information provided by the related images. There is still room for improvement in their performance. Motivated by these two aspects, we propose a novel internal-external representation learning (UIERL) network to better perform UIE tasks with internal and external information, simultaneously. In the internal representation learning stage, a new depth-based region feature guidance network is designed, including a region segmentation module based on scene depth to sense regions with different quality levels, followed by a region-wise space encoder module. With performing region-wise feature learning for regions with different quality separately, the network provides an effective guidance for global features and thus guides intra-image differentiated enhancement. In the external representation learning stage, we first propose an external information extraction network to mine the rich external information in the related images. Then, internal and external features interact with each other via the proposed external-assist-internal module (external features are updated with the help of internal features) and internal-assist-external module (internal features are updated with the help of external features). In this way, our UIERL fully explores the rich internal and external information to better enhance a single image. All results show that our method can achieve state-of-the-art performance on five benchmarks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
朱朱发布了新的文献求助10
1秒前
sin完成签到 ,获得积分10
1秒前
斑马兽完成签到,获得积分10
2秒前
乐乐的应助被gaoyi12356采纳,获得10
2秒前
YXH给YXH的求助进行了留言
3秒前
4秒前
4秒前
liu45kf完成签到,获得积分10
4秒前
kongqing完成签到,获得积分10
4秒前
拼搏的大地完成签到,获得积分10
4秒前
mzn6664发布了新的文献求助10
5秒前
黄毛虎发布了新的文献求助10
5秒前
6秒前
阿北洛完成签到,获得积分10
8秒前
8秒前
Jasper的应助被gaoyi12356采纳,获得10
9秒前
ian发布了新的文献求助10
9秒前
彤航完成签到,获得积分10
10秒前
10秒前
吱吱发布了新的文献求助10
10秒前
Qin完成签到,获得积分0
10秒前
10秒前
七七发布了新的文献求助10
12秒前
所所的应助被鸡翅爱睡觉采纳,获得10
12秒前
luan发布了新的文献求助10
13秒前
牛哞完成签到,获得积分10
14秒前
德烁完成签到,获得积分10
14秒前
14秒前
小洁完成签到 ,获得积分0
14秒前
Yana完成签到,获得积分10
15秒前
zpl完成签到,获得积分10
15秒前
16秒前
黄毛虎发布了新的文献求助10
16秒前
火星上的煎蛋的应助被小SCI采纳,获得10
16秒前
dxftx发布了新的文献求助10
17秒前
秋风的应助被leotao采纳,获得10
18秒前
小溪苏完成签到 ,获得积分10
18秒前
19秒前
田様的应助被gaoyi12356采纳,获得10
19秒前
放鸿鸟于飞完成签到,获得积分10
19秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8187480
求助须知:如何正确求助?哪些是违规求助? 9575554
关于积分的说明 21841909
捐赠科研通 7785230
什么是DOI,文献DOI怎么找? 3434949
关于科研通互助平台的介绍 2559412
邀请新用户注册赠送积分活动 2481898