Generalized Video Deblurring for Dynamic Scenes

TL;DR

This paper introduces a generalized video deblurring approach capable of handling dynamic scenes with complex, spatially varying blurs by jointly estimating optical flows and latent frames within a unified energy model.

Contribution

It presents a novel energy-based framework that simultaneously estimates optical flows and deblurred frames, addressing limitations of static-scene assumptions in prior methods.

Findings

Outperforms state-of-the-art methods in real challenging videos

Effectively handles diverse blur sources like camera shake and moving objects

Achieves accurate optical flow estimation in blurry frames

Abstract

Several state-of-the-art video deblurring methods are based on a strong assumption that the captured scenes are static. These methods fail to deblur blurry videos in dynamic scenes. We propose a video deblurring method to deal with general blurs inherent in dynamic scenes, contrary to other methods. To handle locally varying and general blurs caused by various sources, such as camera shake, moving objects, and depth variation in a scene, we approximate pixel-wise kernel with bidirectional optical flows. Therefore, we propose a single energy model that simultaneously estimates optical flows and latent frames to solve our deblurring problem. We also provide a framework and efficient solvers to optimize the energy model. By minimizing the proposed energy function, we achieve significant improvements in removing blurs and estimating accurate optical flows in blurry frames. Extensive experimental results demonstrate the superiority of the proposed method in real and challenging videos that state-of-the-art methods fail in either deblurring or optical flow estimation.