Splatting-based Synthesis for Video Frame Interpolation
This addresses the challenge of deploying neural network-based frame interpolation in practical applications like video editors by improving speed and high-resolution performance.
The paper tackles the problem of video frame interpolation by proposing a deep learning approach that uses splatting to synthesize interpolated frames, achieving faster performance and new state-of-the-art results at high resolutions.
Frame interpolation is an essential video processing technique that adjusts the temporal resolution of an image sequence. While deep learning has brought great improvements to the area of video frame interpolation, techniques that make use of neural networks can typically not easily be deployed in practical applications like a video editor since they are either computationally too demanding or fail at high resolutions. In contrast, we propose a deep learning approach that solely relies on splatting to synthesize interpolated frames. This splatting-based synthesis for video frame interpolation is not only much faster than similar approaches, especially for multi-frame interpolation, but can also yield new state-of-the-art results at high resolutions.