已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

Color Correction Meets Cross-Spectral Refinement: A Distribution-Aware Diffusion for Underwater Image Restoration

计算机科学 计算机视觉 图像复原 稳健性(进化) 人工智能 颜色校正 水下 小波 像素 小波变换 图像处理 降噪 图像形成 频道(广播) 噪音(视频) 彩色图像 降级(电信) 色彩平衡 特征提取 信号(编程语言) 计算复杂性理论 人工神经网络
作者
Laibin Chang,Yunke Wang,Bo Du,Chang Xu
出处
期刊:IEEE Transactions on Multimedia [Institute of Electrical and Electronics Engineers]
卷期号:28: 3792-3806 被引量:20
标识
DOI:10.1109/tmm.2026.3654357
摘要

Underwater imaging is often plagued by significant degradation in visual quality, primarily due to the effects of light absorption and scattering in water. Although recent underwater image enhancement (UIE) methods rely on the current advances in deep neural network architecture designs, there is still considerable room for improvement in cross-scene robustness and computational efficiency. Diffusion models have shown great success in image generation, prompting us to explore their application to UIE tasks. However, directly applying them to UIE tasks will pose two challenges,i.e., high computational budget and color unbalanced perturbations. To tackle these issues, we propose DiffColor, a distribution-aware diffusion and cross-spectral refinement model for efficient UIE. Unlike single-noise image restoration tasks, underwater imaging exhibits unbalanced channel distributions due to the selective absorption of light by water. To address this, we design the Global Color Correction to balance the diverse color shifts, thereby avoiding potential global degradation disturbances during the denoising process. Instead of diffusing in the raw pixel space, we transform the image into the wavelet domain to obtain such low-frequency and high-frequency spectra. For the sacrificed image details caused by underwater scattering, we further present the Cross-Spectral Detail Refinement to enhance the high-frequency details, which are then integrated with the low-frequency signal as a dual-condition for guiding the diffusion. This strategy ensures the high-fidelity of sampled content and compensates for the sacrificed details. Extensive experiments demonstrate the superior performance of DiffColor over state-of-the-art methods in both quantitative and qualitative evaluations.
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
orixero的应助被方九九采纳,获得10
刚刚
fanxy发布了新的文献求助200
刚刚
keithyoung发布了新的文献求助10
刚刚
刚刚
KalEl发布了新的文献求助10
1秒前
SDDSD发布了新的文献求助10
1秒前
1秒前
FashionBoy的应助被lois采纳,获得20
2秒前
2秒前
wan发布了新的文献求助10
2秒前
大模型的应助被小王采纳,获得10
2秒前
3秒前
4秒前
4秒前
香蕉觅云的应助被zzcs33采纳,获得10
4秒前
4秒前
5秒前
5秒前
脑洞疼的应助被Darkangel采纳,获得10
5秒前
心殇完成签到,获得积分10
6秒前
大模型的应助被勤恳南风采纳,获得10
6秒前
6秒前
爆米花的应助被fortuna采纳,获得10
7秒前
8秒前
HAOna完成签到 ,获得积分10
10秒前
10秒前
每天100次的应助被蓉蓉全肯定采纳,获得20
10秒前
wydkyd发布了新的文献求助10
10秒前
10秒前
顺颂时祺完成签到,获得积分10
10秒前
FashionBoy的应助被keithyoung采纳,获得10
12秒前
12秒前
传奇3的应助被SDDSD采纳,获得10
12秒前
aaa发布了新的文献求助10
12秒前
大个的应助被小晓采纳,获得10
13秒前
13秒前
coco仓完成签到 ,获得积分10
13秒前
14秒前
16秒前
668898发布了新的文献求助10
17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 1500
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
John McDowells Bildungstheorie 800
八旗制度の研究 600
What Else Can I Tell You?: A Pragmatic Study of English Rhetorical Questions as Discursive and Argumentative Acts 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 8158064
求助须知:如何正确求助?哪些是违规求助? 9553987
关于积分的说明 21716926
捐赠科研通 7747422
什么是DOI,文献DOI怎么找? 3426934
关于科研通互助平台的介绍 2551676
邀请新用户注册赠送积分活动 2471057