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
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI