Blurry Video Compression: A Trade-off between Visual Enhancement and Data Compression

TL;DR

This paper introduces a novel video compression framework that balances visual enhancement and data reduction, effectively handling blurry videos caused by camera settings or scene dynamics, outperforming existing methods.

Contribution

It formulates video compression as a min-max optimization problem to address blur and quality trade-offs, providing a new effective training strategy and framework.

Findings

Outperforms state-of-the-art VC methods on benchmark datasets

Effectively handles videos with motion blur and low frame rate

Demonstrates robustness across various real-world scenarios

Abstract

Existing video compression (VC) methods primarily aim to reduce the spatial and temporal redundancies between consecutive frames in a video while preserving its quality. In this regard, previous works have achieved remarkable results on videos acquired under specific settings such as instant (known) exposure time and shutter speed which often result in sharp videos. However, when these methods are evaluated on videos captured under different temporal priors, which lead to degradations like motion blur and low frame rate, they fail to maintain the quality of the contents. In this work, we tackle the VC problem in a general scenario where a given video can be blurry due to predefined camera settings or dynamics in the scene. By exploiting the natural trade-off between visual enhancement and data compression, we formulate VC as a min-max optimization problem and propose an effective framework and training strategy to tackle the problem. Extensive experimental results on several benchmark datasets confirm the effectiveness of our method compared to several state-of-the-art VC approaches.