Deep Video Inpainting
This addresses the problem of filling spatio-temporal holes in videos for applications like video editing, offering a fast and effective solution compared to slower optimization-based approaches.
The paper tackles video inpainting by proposing a deep network architecture that collects and refines information from neighbor frames with temporal consistency modules, resulting in semantically correct and temporally smooth videos that run in near real-time, generating competitive results compared to prior methods.
Video inpainting aims to fill spatio-temporal holes with plausible content in a video. Despite tremendous progress of deep neural networks for image inpainting, it is challenging to extend these methods to the video domain due to the additional time dimension. In this work, we propose a novel deep network architecture for fast video inpainting. Built upon an image-based encoder-decoder model, our framework is designed to collect and refine information from neighbor frames and synthesize still-unknown regions. At the same time, the output is enforced to be temporally consistent by a recurrent feedback and a temporal memory module. Compared with the state-of-the-art image inpainting algorithm, our method produces videos that are much more semantically correct and temporally smooth. In contrast to the prior video completion method which relies on time-consuming optimization, our method runs in near real-time while generating competitive video results. Finally, we applied our framework to video retargeting task, and obtain visually pleasing results.