arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2507.16683cs.CV

QRetinex-Net:面向低层计算机视觉应用的四元数值 Retinex 分解

QRetinex-Net: Quaternion-Valued Retinex Decomposition for Low-Level Computer Vision Applications

City University of New York(纽约市立大学);College of Staten Island(斯塔滕岛学院)

Sos Agaian, Vladimir Frants

AI总结:

本文提出首个四元数 Retinex 模型 QRetinex-Net,利用 Hamilton 乘积联合建模颜色通道,并以反射率一致性指数评估不变性,在三类低层视觉任务中较主流方法提升 2–11%。

摘要:

在低光照条件下拍摄的图像通常会出现色偏、低对比度、噪声和其他伪影,这些问题会损害计算机视觉的准确性。Retinex 理论通过将图像 S 视为反射率 R 与光照 I 的逐像素乘积来解决该问题,这反映了人类在变化光照下感知稳定物体颜色的方式。这种分解是不适定的,而经典 Retinex 模型存在四个关键缺陷:(i)它们独立处理红、绿、蓝三个通道;(ii)它们缺乏关于颜色视觉的神经科学模型;(iii)它们无法完美重建输入图像;以及(iv)它们不能解释人类的颜色恒常性。我们提出首个四元数 Retinex 表述,其中场景被写为四元数值反射率与光照的 Hamilton 乘积。为衡量反射率保持不变的程度,我们提出了 Reflectance Consistency Index(反射率一致性指数)。在低光照裂缝检测、不同光照下的人脸检测以及红外-可见光融合任务上的测试表明,相比领先方法,其性能提升 2–11%,并具有更好的颜色保真度、更低的噪声和更高的反射率稳定性。

英文摘要:

Images taken in low light often show color shift, low contrast, noise, and other artifacts that hurt computer-vision accuracy. Retinex theory addresses this by viewing an image S as the pixel-wise product of reflectance R and illumination I, mirroring the way people perceive stable object colors under changing light. The decomposition is ill-posed, and classic Retinex models have four key flaws: (i) they treat the red, green, and blue channels independently; (ii) they lack a neuroscientific model of color vision; (iii) they cannot perfectly rebuild the input image; and (iv) they do not explain human color constancy. We introduce the first Quaternion Retinex formulation, in which the scene is written as the Hamilton product of quaternion-valued reflectance and illumination. To gauge how well reflectance stays invariant, we propose the Reflectance Consistency Index. Tests on low-light crack inspection, face detection under varied lighting, and infrared-visible fusion show gains of 2-11 percent over leading methods, with better color fidelity, lower noise, and higher reflectance stability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑