Computational Framework for Estimating Relative Gaussian Blur Kernels between Image Pairs

TL;DR

This paper presents a real-time, zero-training computational framework for estimating Gaussian blur kernels between image pairs, enabling accurate blur measurement and defocus correction in practical applications.

Contribution

It introduces a novel analytic, non-learning-based method for estimating Gaussian blur kernels directly from image pairs, suitable for real-time use.

Findings

Achieves mean absolute error below 1.7% in synthetic blur estimation

Discrepancy under 2% when applying defocus filters

Effective on real images for blur measurement

Abstract

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.