Real-World Nighttime Image Dehazing via Bayesian-Based Fractional-Order Variational Model

分段 计算机科学 计算机视觉 人工智能 先验概率 亮度 平滑度 噪音(视频) 图像(数学) 缩小 剪切波 算法 图像复原 颜色恒定性 反射率 中间视觉 光度立体 全局照明 分割 噪音的颜色 最优化问题 数学 反照率(炼金术) 反射(计算机编程) 背景减法 分歧(语言学) 图像质量 图像分割 卷积神经网络 轻巧 图像处理 背景图像
作者
Yun Liu,Tao Li,Zichen Zhou,Wenqi Ren,Weisi Lin
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:35: 4673-4685 被引量:41
标识
DOI:10.1109/tip.2026.3687080
摘要

Images captured under real-world nighttime haze conditions often suffer from severe degradations, including low visibility, color distortion, and reduced contrast, which not only impair visual perception but also degrade the performance of vision-based tasks. However, existing dehazing methods are mainly designed for daytime scenarios and struggle to cope with the complex illumination and scattering characteristics of nighttime hazy images. In this paper, we propose a novel Bayesian-based variational framework with fractional-order constraints for real-world nighttime image dehazing. First, a simplified physical model is constructed to characterize nighttime hazy images, accounting for haze, low-light conditions, Poisson noise, and glow degradations. An anisotropic pre-processing strategy is iteratively applied in the Lab color space to remove glow effects. Subsequently, illumination and reflectance estimation within our constructed physical model is formulated as a maximum a-posteriori (MAP) problem, which is then approximated as a unified variational optimization function. To impose prior constraints, two fractional-order terms are introduced as priors to regulate the illumination and reflectance, promoting piecewise smoothness in illumination and preserving sharp edges and fine textures in reflectance. The resulting variational model is efficiently solved using the alternating direction minimization method. Finally, the estimated illumination and reflectance are enhanced via spatial-domain gamma correction for brightness adjustment and frequency-domain processing for texture detail enhancement. Extensive experiments on real-world datasets demonstrate that the proposed framework outperforms state-of-the-art dehazing methods in both qualitative and quantitative evaluations. Besides, our algorithm generalizes effectively to both other degraded scenes and high-level vision tasks.
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
落雁沙完成签到,获得积分10
1秒前
1秒前
兔子发布了新的文献求助10
2秒前
小浩浩发布了新的文献求助20
3秒前
Ava的应助被Mr鹿采纳,获得10
3秒前
3秒前
壮观雁易发布了新的文献求助10
4秒前
5秒前
11完成签到,获得积分10
5秒前
Yuther完成签到 ,获得积分10
5秒前
6秒前
李治海完成签到,获得积分10
7秒前
7秒前
7秒前
伊森完成签到,获得积分10
8秒前
11发布了新的文献求助10
8秒前
小胖卷毛完成签到,获得积分10
9秒前
9秒前
9秒前
10秒前
搜集达人的应助被醒着像睡着采纳,获得10
10秒前
10秒前
10秒前
NexusExplorer的应助被小鱼采纳,获得10
11秒前
邦邦发布了新的文献求助10
12秒前
12秒前
Wyh完成签到 ,获得积分10
13秒前
dong发布了新的文献求助10
14秒前
初景发布了新的文献求助10
14秒前
12完成签到,获得积分20
15秒前
15秒前
shine发布了新的文献求助10
16秒前
17秒前
李健的小迷弟的应助被kanraku采纳,获得10
17秒前
17秒前
852的应助被科研通管家采纳,获得10
18秒前
Crssss的应助被科研通管家采纳,获得10
18秒前
爆米花的应助被科研通管家采纳,获得10
18秒前
18秒前
英姑的应助被科研通管家采纳,获得10
18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
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
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
基于结构调控的功能化水诱导发电材料与器件研究 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 8189431
求助须知:如何正确求助?哪些是违规求助? 9576755
关于积分的说明 21849578
捐赠科研通 7787361
什么是DOI,文献DOI怎么找? 3435577
关于科研通互助平台的介绍 2559772
邀请新用户注册赠送积分活动 2482529