Mirrors/ECCV2022-RIFE
1
0
Fork 0
mirror of https://github.com/hzwer/ECCV2022-RIFE.git synced 2026-02-24 04:19:41 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
hzwer
2020-11-17 12:33:10 +08:00
committed by GitHub
parent 382904d0b7
commit fc456bc844
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -13,7 +13,7 @@ Our model can run 30+FPS for 2X 720p interpolation on a 2080Ti GPU. Currently ou
![Demo](./demo/I2_slomo_clipped.gif)
## Abstract
We propose a real-time intermediate flow estimation algorithm (RIFE) for video frame interpolation (VFI). Most existing methods first estimate the bi-directional optical flows, and then linearly combine them to approximate intermediate flows, leading to artifacts around motion boundaries. We design an intermediate flow model named IFNet that can directly estimate the intermediate flows from coarse to fine. We then warp the input frames according to the estimated intermediate flows and employ a fusion process to compute final results. Based on our proposed leakage distillation, RIFE can be trained end-to-end and achieve excellent performance. Experiments demonstrate that RIFE is significantly faster than existing flow-based VFI methods and achieves state-of-the-art index on several benchmarks.
We propose RIFE, a Real-time Intermediate Flow Estimation algorithm, with applications to Video Frame Interpolation (VFI). Most existing flow estimation methods first estimate the bi-directional optical flows, and then linearly combine them to approximate intermediate flows, leading to artifacts on motion boundaries. We design a Neural Network named IFNet, that can directly estimate the intermediate flows from images. When interpolating videos, we can warp the frames according to the estimated intermediate flows and employ a fusion process to compute final results. Based on our proposed leakage distillation loss, RIFE can be trained in an end-to-end fashion. Experiments demonstrate that our method is significantly faster than existing VFI methods and can achieve state-of-the-art performance on public benchmarks.
## Dependencies
```