无需训练，实时计算两张图间的模糊程度差异。
Computational Framework for Estimating Relative Gaussian Blur Kernels between Image Pairs
- 基于解析表达式离散计算模糊核，实现快速估计。
- 合成模糊值误差低于1.7%，图像亮度估计偏差小于2%。
- 适合需要精准模糊分析的图像处理场景。
在先前验证高斯模型有效性的基础上，本文提出一种零训练的前向计算框架，可在实时应用中实现该模型。该框架基于从清晰图像推导出模糊图像的解析表达式的离散计算，适用于高斯核标准差范围，并通过选择最佳匹配来确定模糊参数。在某些像素点上，解析表达式存在多个解，但通过邻近点的相似性度量将其筛选为唯一解。框架可处理两张图像互为部分模糊版本的情况。在真实图像上的实验表明，所提方法在估计合成模糊值时，平均绝对误差（MAE）低于1.7%；将提取的去焦滤波器应用于较不模糊的图像后，实际图像强度与估计值之间的差异保持在2%以内。
原文摘要 · Abstract (English)
Following the earlier verification for Gaussian model in \cite{ASaa2026}, this paper introduces a zero training forward computational framework for the model to realize it in real time applications. The framework is based on discrete calculation of the analytic expression of the defocused image from the sharper one for the application range of the standard deviation of the Gaussian kernels and selecting the best matches. The analytic expression yields multiple solutions at certain image points, but is filtered down to a single solution using similarity measures over neighboring points.The framework is structured to handle cases where two given images are partial blurred versions of each other. Experimental evaluations on real images demonstrate that the proposed framework achieves a mean absolute error (MAE) below $1.7\%$ in estimating synthetic blur values. Furthermore, the discrepancy between actual blurred image intensities and their corresponding estimates remains under $2\%$, obtained by applying the extracted defocus filters to less blurred images.
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。