VDPI: Video Deblurring with Pseudo-inverse Modeling

TL;DR

This paper introduces a novel deep learning approach for video deblurring that incorporates the image-formation model via pseudo-inverse estimation, significantly enhancing deblurring performance across various datasets.

Contribution

It proposes integrating pseudo-inverse modeling into deep networks for video deblurring, combining model-based and deep learning techniques for improved results.

Findings

Significant performance improvements on multiple datasets.

Enhanced generalization across different scenarios and cameras.

Effective combination of traditional model-based methods with deep learning.

Abstract

Video deblurring is a challenging task that aims to recover sharp sequences from blur and noisy observations. The image-formation model plays a crucial role in traditional model-based methods, constraining the possible solutions. However, this is only the case for some deep learning-based methods. Despite deep-learning models achieving better results, traditional model-based methods remain widely popular due to their flexibility. An increasing number of scholars combine the two to achieve better deblurring performance. This paper proposes introducing knowledge of the image-formation model into a deep learning network by using the pseudo-inverse of the blur. We use a deep network to fit the blurring and estimate pseudo-inverse. Then, we use this estimation, combined with a variational deep-learning network, to deblur the video sequence. Notably, our experimental results demonstrate that such modifications can significantly improve the performance of deep learning models for video deblurring. Furthermore, our experiments on different datasets achieved notable performance improvements, proving that our proposed method can generalize to different scenarios and cameras.