用四元数建模光照反射，提升低光图像色彩稳定性和清晰度。
QRetinex-Net: Quaternion-Valued Retinex Decomposition for Low-Level Computer Vision Applications
- 提出四元数形式的Retinex分解，统一处理彩色通道。
- 在裂缝检测等任务中比顶尖方法提升2-11%准确率。
- 适合低光视觉、红外可见光融合等需色彩稳定的场景。
低光环境下拍摄的图像常出现色彩偏移、对比度低、噪声等问题，影响计算机视觉性能。Retinex理论将图像S视为反射率R与光照I的逐像素乘积，模拟人眼对物体颜色的恒常感知。传统模型存在四大缺陷：(i) 独立处理RGB三通道；(ii) 缺乏神经科学支持的颜色视觉模型；(iii) 无法完美重建输入图像；(iv) 无法解释人类颜色恒常性。本文首次提出四元数形式的Retinex模型，将场景表示为四元数反射率与光照的哈密顿乘积。为评估反射率不变性，提出反射率一致性指数。在低光裂缝检测、不同光照下人脸识别及红外-可见光融合任务中，相比领先方法提升2-11个百分点，且具备更优的色彩保真度、更低噪声和更高反射率稳定性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。