Generalized Video Deblurring for Dynamic Scenes
This addresses the problem of blurry videos in dynamic scenes for applications like video enhancement, but it is incremental as it builds on prior deblurring techniques.
The paper tackles video deblurring in dynamic scenes, where existing methods fail due to assumptions of static scenes, and proposes a method using bidirectional optical flows to approximate pixel-wise kernels, achieving significant improvements in deblurring and optical flow estimation as shown in extensive experiments.
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.