Deep Color Compensation for Generalized Underwater Image Enhancement

人工智能 计算机科学 水下 颜色校正 计算机视觉 基本事实 概率逻辑 补偿(心理学) 模式识别(心理学) 图像(数学) 精神分析 心理学 海洋学 地质学
作者
Yuan Rao,Wenjie Liu,Kunqian Li,Hao Fan,Sen Wang,Junyu Dong
出处
期刊:IEEE Transactions on Circuits and Systems for Video Technology [Institute of Electrical and Electronics Engineers]
卷期号:34 (4): 2577-2590 被引量:3
标识
DOI:10.1109/tcsvt.2023.3305777
摘要

Underwater images suffer from quality degradation due to the underwater light absorption and scattering. It remains challenging to enhance underwater images using deep learning-based methods since the scarcity of real-world underwater images and their enhanced counterparts. Although existing works manually select well-enhanced images as reference images to train enhancement networks in an end-to-end manner, their performance tends to be inferior in some scenarios. We argue that the manually selected reference images cannot approximate their ground truth perfectly, leading to imbalanced learning and domain shift in enhancement networks. To address this issue, we analyse widely used underwater datasets from the perspective of color spectrum distribution and surprisingly find the sound color spectrum distribution of the enhanced reference images compared to in-air datasets. Based on this perceptive observation, instead of directly learning the enhancement mapping, we propose a novel methodology to learn color compensation for general purposes. Specifically, we present a probabilistic color compensation network that estimates the probabilistic distribution of colors by multi-scale volumetric fusion of texture and color features. We further propose a novel two-stage enhancement framework that first performs color compensation and then enhancement, which is highly flexible to be integrated with an existing enhancement method without tuning. Extensive experiments on underwater image enhancement across various challenging scenarios show that our proposed approach consistently improves the results of the popular conventional and learning-based methods by a significant margin. Moreover, our enhanced images achieve superior performance on underwater salient object detection and visual 3D reconstruction, demonstrating that our method can successfully break through the generalization bottleneck of existing learning-based enhancement models. Our implementation will be made available at https://github.com/Ray2OUC/P2CNet.
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
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
刚刚
Doctor.Xie完成签到,获得积分10
刚刚
zzyyy完成签到,获得积分10
1秒前
2秒前
Ruliiiii发布了新的文献求助10
2秒前
宓天问发布了新的文献求助10
2秒前
卤蛋今天没学习完成签到,获得积分10
4秒前
4秒前
贪玩海之完成签到,获得积分10
5秒前
QQ完成签到,获得积分10
5秒前
6秒前
奶味仙豆糕完成签到,获得积分10
6秒前
6秒前
7秒前
dongxiaomai发布了新的文献求助30
8秒前
搜集达人应助周斌采纳,获得10
8秒前
Yziii应助ZZzz采纳,获得20
8秒前
8秒前
9秒前
wanci应助TheDay采纳,获得10
10秒前
呆瓜完成签到,获得积分10
10秒前
11秒前
明亮访烟完成签到,获得积分10
11秒前
11秒前
juziyaya应助天空之城采纳,获得20
12秒前
完美世界应助Raye采纳,获得10
12秒前
12秒前
12秒前
王可爱发布了新的文献求助10
12秒前
13秒前
13秒前
桐桐应助lenny采纳,获得10
14秒前
明亮访烟发布了新的文献求助10
14秒前
陈皮完成签到,获得积分10
14秒前
wzx_01完成签到,获得积分10
14秒前
psybao完成签到,获得积分10
14秒前
碗碗完成签到,获得积分10
14秒前
14秒前
14秒前
15秒前
高分求助中
The late Devonian Standard Conodont Zonation 2000
Nickel superalloy market size, share, growth, trends, and forecast 2023-2030 2000
The Lali Section: An Excellent Reference Section for Upper - Devonian in South China 1500
Very-high-order BVD Schemes Using β-variable THINC Method 870
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 800
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
Fundamentals of Dispersed Multiphase Flows 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3254632
求助须知:如何正确求助?哪些是违规求助? 2896806
关于积分的说明 8294490
捐赠科研通 2565750
什么是DOI,文献DOI怎么找? 1393327
科研通“疑难数据库(出版商)”最低求助积分说明 652471
邀请新用户注册赠送积分活动 630040