A Novel Approach for Translational Motion Blur Estimation Based on Radon Transform

Motion blur, resulting from relative motion between a camera and a scene during exposure, presents a significant challenge in digital imaging. This paper introduces a novel approach for Point Spread Function (PSF) estimation tailored specifically for cases of linear motion blur. The proposed method aims to improve the accuracy of PSF estimation, leading to more effective image restoration. To assess its performance, we conduct a comparative analysis against two established techniques: a Convolutional Neural Network (CNN)-based restoration model and a traditional PSF estimation method that served as the starting point for our study. Quantitative and qualitative evaluations demonstrate that our approach achieves superior deblurring performance, producing images with enhanced sharpness and structural fidelity. The results highlight the effectiveness of our method in restoring motionblurred images.