Move to tf.data, for much more efficient data loading with less code.

[voxel-flow] / README.md

diff --git a/README.md b/README.md
index 5abb631c2e8ae5e43b055e7dddbe13be81c568da..7db22b6fd304489142cf06da57b3dbd18e6de952 100755 (executable)
--- a/README.md
+++ b/README.md
@@ -1,13 +1,15 @@
 # Video Frame Synthesis using Deep Voxel Flow
-[[Project]](https://liuziwei7.github.io/projects/VoxelFlow) [[Paper]](https://arxiv.org/abs/1702.02463)   
+We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). Our method requires no human supervision, and any video can be used as training data by dropping, and then learning to predict, existing frames. `Deep Voxel Flow (DVF)` 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.
 
-<img src='./misc/demo.gif' width=640>
+[[Project]](https://liuziwei7.github.io/projects/VoxelFlow) [[Paper]](https://arxiv.org/abs/1702.02463) [[Demo]](https://liuziwei7.github.io/projects/voxelflow/demo.html)      
+
+<img src='./misc/demo.gif' width=810>
 
 ## Overview
 `Deep Voxel Flow (DVF)` is the author's re-implementation of the video frame synthesizer described in:  
 "Video Frame Synthesis using Deep Voxel Flow"   
-[Ziwei Liu](https://liuziwei7.github.io/), [Raymond A. Yeh](http://www.isle.illinois.edu/~yeh17/), [Xiaoou Tang](http://www.ie.cuhk.edu.hk/people/xotang.shtml), [Yiming Liu](http://bitstream9.me/), [Aseem Agarwala](http://www.agarwala.org/)
-In International Conference on Computer Vision (ICCV) 2017, Oral Presentation
+[Ziwei Liu](https://liuziwei7.github.io/), [Raymond A. Yeh](http://www.isle.illinois.edu/~yeh17/), [Xiaoou Tang](http://www.ie.cuhk.edu.hk/people/xotang.shtml), [Yiming Liu](http://bitstream9.me/), [Aseem Agarwala](http://www.agarwala.org/) (CUHK & UIUC & Google Research)
+in International Conference on Computer Vision (ICCV) 2017, Oral Presentation
 
 <img src='./misc/demo_teaser.jpg' width=800>
 
@@ -25,6 +27,10 @@ python voxel_flow_train.py --subset=train
 ``` bash
 python voxel_flow_train.py --subset=test
 ```
+* Run the evaluation script:
+``` bash
+matlab eval_voxelflow.m
+```
 
 ## License and Citation
 The use of this software is RESTRICTED to **non-commercial research and educational purposes**.