Video Frame Synthesis Using Deep Voxel Flow

Ziwei Liu, Raymond A. Yeh, Xiaoou Tang, Yiming Liu, Aseem Agarwala; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4463-4471

Abstract


We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). This problem is challenging because video appearance and motion can be highly complex. Traditional optical-flow-based solutions often fail where flow estimation is challenging, while newer neural-network-based methods that hallucinate pixel values directly often produce blurry results. We combine the advantages of these two methods by training a deep network that learns to synthesize video frames by flowing pixel values from existing ones, which we call deep voxel flow. Our method requires no human supervision, and any video can be used as training data by dropping, and then learning to predict, existing frames. The technique is efficient, and can be applied at any video resolution. We demonstrate that our method produces results that both quantitatively and qualitatively improve upon the state-of-the-art.

Related Material


[pdf] [arXiv] [video]
[bibtex]
@InProceedings{Liu_2017_ICCV,
author = {Liu, Ziwei and Yeh, Raymond A. and Tang, Xiaoou and Liu, Yiming and Agarwala, Aseem},
title = {Video Frame Synthesis Using Deep Voxel Flow},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}