diff options
| author | sniklaus <simon.niklaus@outlook.com> | 2018-03-30 22:15:16 -0700 |
|---|---|---|
| committer | sniklaus <simon.niklaus@outlook.com> | 2018-03-30 22:15:16 -0700 |
| commit | 9cdabbe592c822586b075c6b7659de995613025e (patch) | |
| tree | 164b27994089499034a29737d591c27f8b3c15c9 | |
| parent | a536e069fb402dd3a891f93faa9d2ef3825a1f29 (diff) | |
no message
| -rw-r--r-- | README.md | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -1,5 +1,5 @@ # pytorch-sepconv -Please consider our newest work, [Context-aware Synthesis](http://web.cecs.pdx.edu/~fliu/project/ctxsyn) for Video Frame Interpolation. +**News:** Check our new CVPR 2018 paper on a [faster and higher-quality](http://web.cecs.pdx.edu/~fliu/project/ctxsyn) frame interpolation method. This is a reference implementation of Video Frame Interpolation via Adaptive Separable Convolution [1] using PyTorch. Given two frames, it will make use of [adaptive convolution](http://graphics.cs.pdx.edu/project/adaconv) [2] in a separable manner to interpolate the intermediate frame. Should you be making use of our work, please cite our paper [1]. |