From 088beb1e658c4977b0439bf6238b556d85157a52 Mon Sep 17 00:00:00 2001
From: hzwer <598460606@163.com>
Date: Fri, 13 Nov 2020 18:41:50 +0800
Subject: [PATCH] Updated demos

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 4fa4d45..2a6dbef 100644
--- a/README.md
+++ b/README.md
@@ -4,8 +4,8 @@
 
 Our method support CPU and GPU with CUDA.
 
-![Demo](./demo/I0_slomo.gif)
-![Demo](./demo/I2_slomo.gif)
+![Demo](./demo/I0_slomo_clipped.gif)
+![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.