# Computational Framework for Estimating Relative Gaussian Blur Kernels between Image Pairs

arXiv: https://arxiv.org/abs/2601.18099 · HTML: https://mlsanity.com/paper/2601.18099/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 54 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 9 of 9)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields](https://mlsanity.com/paper/1502.07411/) (2015)
- [Defocus Deblurring Using Dual-Pixel Data](https://mlsanity.com/paper/2005.00305/) (2020)
- [Deep Convolutional Neural Fields for Depth Estimation from a Single Image](https://mlsanity.com/paper/1411.6387/) (2014)
- [DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling](https://mlsanity.com/paper/2001.00987/) (2019)
- [DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations](https://mlsanity.com/paper/1510.02927/) (2015)
- [GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation](https://mlsanity.com/paper/2012.06980/) (2020)
- [Exact Blur Measure Outperforms Conventional Learned Features for Depth Finding](https://mlsanity.com/paper/1709.00072/) (2017)

## Abstract (arXiv)

Following the earlier verification for Gaussian model in citeASaa2026, 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.