SelfHVD: Self-Supervised Handheld Video Deblurring

TL;DR

SelfHVD introduces a self-supervised approach for handheld video deblurring that leverages sharp clues within videos and novel regularization techniques, outperforming existing methods on synthetic and real datasets.

Contribution

The paper presents a self-supervised deblurring framework with a novel data creation method and regularization to improve real-world handheld video deblurring performance.

Findings

Outperforms existing self-supervised deblurring methods on multiple datasets.

Effectively utilizes sharp clues for training without paired sharp-blurry data.

Constructs synthetic and real-world datasets for evaluation.

Abstract

Shooting video with handheld shooting devices often results in blurry frames due to shaking hands and other instability factors. Although previous video deblurring methods have achieved impressive progress, they still struggle to perform satisfactorily on real-world handheld video due to the blur domain gap between training and testing data. To address the issue, we propose a self-supervised method for handheld video deblurring, which is driven by sharp clues in the video. First, to train the deblurring model, we extract the sharp clues from the video and take them as misalignment labels of neighboring blurry frames. Second, to improve the deblurring ability of the model, we propose a novel Self-Enhanced Video Deblurring (SEVD) method to create higher-quality paired video data. Third, we propose a Self-Constrained Spatial Consistency Maintenance (SCSCM) method to regularize the model, preventing position shifts between the output and input frames. Moreover, we construct synthetic and real-world handheld video datasets for handheld video deblurring. Extensive experiments on these and other common real-world datasets demonstrate that our method significantly outperforms existing self-supervised ones. The code and datasets are publicly available at https://cshonglei.github.io/SelfHVD.