Video Deblurring by Sharpness Prior Detection and Edge Information

TL;DR

This paper introduces a new dataset and a novel attention-based model for video deblurring that leverages sharp frame detection and edge information, significantly improving deblurring performance.

Contribution

It presents GoProRS, a flexible dataset with customizable sharp frame frequency, and SPEINet, a lightweight model that enhances deblurring by integrating sharp frame features.

Findings

SPEINet outperforms state-of-the-art methods with +3.2% PSNR.

GoProRS enables more diverse training scenarios.

The model effectively utilizes sharp frame detection and edge features.

Abstract

Video deblurring is essential task for autonomous driving, facial recognition, and security surveillance. Traditional methods directly estimate motion blur kernels, often introducing artifacts and leading to poor results. Recent approaches utilize the detection of sharp frames within video sequences to enhance deblurring. However, existing datasets rely on fixed number of sharp frames, which may be too restrictive for some applications and may introduce a bias during model training. To address these limitations and enhance domain adaptability, this work first introduces GoPro Random Sharp (GoProRS), a new dataset where the the frequency of sharp frames within the sequence is customizable, allowing more diverse training and testing scenarios. Furthermore, it presents a novel video deblurring model, called SPEINet, that integrates sharp frame features into blurry frame reconstruction through an attention-based encoder-decoder architecture, a lightweight yet robust sharp frame detection and an edge extraction phase. Extensive experimental results demonstrate that SPEINet outperforms state-of-the-art methods across multiple datasets, achieving an average of +3.2% PSNR improvement over recent techniques. Given such promising results, we believe that both the proposed model and dataset pave the way for future advancements in video deblurring based on the detection of sharp frames.