# Deep Video Inpainting

## TL;DR

This paper introduces a fast, deep neural network architecture for video inpainting that ensures temporal consistency and outperforms prior methods in speed and quality, enabling near real-time video completion.

## Contribution

The authors propose a novel deep network combining an image-based encoder-decoder with temporal modules for efficient, consistent video inpainting, advancing beyond existing slow optimization-based approaches.

## Key findings

- Produces semantically correct, smooth videos
- Operates in near real-time
- Achieves competitive quality in video retargeting

## Abstract

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.