We propose RIFE, a Real-time Intermediate Flow Estimation algorithm for Video Frame Interpolation (VFI). Most existing flow-based methods first estimate the bi-directional optical flows, then scale and reverse them to approximate intermediate flows, leading to artifacts on motion boundaries. RIFE uses a neural network named IFNet that can directly estimate the intermediate flows from images with much better speed. Based on our proposed leakage distillation loss, RIFE can be trained in an end-to-end fashion. Experiments demonstrate that our method is flexible and can achieve impressive performance on several public benchmarks. The code is available at https://github.com/hzwer/arXiv2020-RIFE.

翻译：我们建议使用实时中流估算算法,即视频框架内插的实时中流估算算法(RIFE),大多数现有的流动方法首先估计双向光学流,然后将范围扩大,将其转换为近似中间流,从而导致运动边界上的人工制品。RIFE使用名为IFNet的神经网络,能够以更快的速度直接估计图像的中间流。根据我们提议的渗漏蒸馏损失,RIFE可以以端到端的方式接受培训。实验表明,我们的方法是灵活的,能够在若干公共基准上达到令人印象深刻的业绩。该代码可在https://github.com/hzwer/arXiv20-RIFE查阅。