Real-Time Intermediate Flow Estimation for Video Frame Interpolation
This addresses the need for efficient and high-quality frame interpolation in video processing and media applications, representing a strong specific gain rather than a foundational advancement.
The paper tackles real-time video frame interpolation by proposing RIFE, a method that uses an end-to-end neural network for intermediate flow estimation, achieving state-of-the-art performance with 4-27 times faster speed than existing methods and better results.
Real-time video frame interpolation (VFI) is very useful in video processing, media players, and display devices. We propose RIFE, a Real-time Intermediate Flow Estimation algorithm for VFI. To realize a high-quality flow-based VFI method, RIFE uses a neural network named IFNet that can estimate the intermediate flows end-to-end with much faster speed. A privileged distillation scheme is designed for stable IFNet training and improve the overall performance. RIFE does not rely on pre-trained optical flow models and can support arbitrary-timestep frame interpolation with the temporal encoding input. Experiments demonstrate that RIFE achieves state-of-the-art performance on several public benchmarks. Compared with the popular SuperSlomo and DAIN methods, RIFE is 4--27 times faster and produces better results. Furthermore, RIFE can be extended to wider applications thanks to temporal encoding. The code is available at https://github.com/megvii-research/ECCV2022-RIFE.