From e16c7793db36272ee9d97a7c1a3e9b907b167b85 Mon Sep 17 00:00:00 2001 From: Ziwei Liu Date: Sun, 4 Feb 2018 17:51:11 -0800 Subject: [PATCH] update readme --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 86ac35e..ae063d0 100755 --- a/README.md +++ b/README.md @@ -1,5 +1,7 @@ # Video Frame Synthesis using Deep Voxel Flow -[[Project]](https://liuziwei7.github.io/projects/VoxelFlow) [[Paper]](https://arxiv.org/abs/1702.02463) [[demo]](https://liuziwei7.github.io/projects/voxelflow/demo.html) +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. + +[[Project]](https://liuziwei7.github.io/projects/VoxelFlow) [[Paper]](https://arxiv.org/abs/1702.02463) [[Demo]](https://liuziwei7.github.io/projects/voxelflow/demo.html) -- 2.39.2