We present a new data-driven video inpainting method for recovering missing regions of video frames. A novel deep learning architecture is proposed which contains two sub-networks: a temporal structure inference network and a spatial detail recovering network. The temporal structure inference network is built upon a 3D fully convolutional architecture: it only learns to complete a low-resolution video volume given the expensive computational cost of 3D convolution. The low resolution result provides temporal guidance to the spatial detail recovering network, which performs image-based inpainting with a 2D fully convolutional network to produce recovered video frames in their original resolution. Such two-step network design ensures both the spatial quality of each frame and the temporal coherence across frames. Our method jointly trains both sub-networks in an end-to-end manner. We provide qualitative and quantitative evaluation on three datasets, demonstrating that our method outperforms previous learning-based video inpainting methods.
@article{arxiv.1806.08482,
title = {Video Inpainting by Jointly Learning Temporal Structure and Spatial Details},
author = {Chuan Wang and Haibin Huang and Xiaoguang Han and Jue Wang},
journal= {arXiv preprint arXiv:1806.08482},
year = {2018}
}