Splatting-based Synthesis for Video Frame Interpolation

TL;DR

This paper introduces a splatting-based deep learning method for video frame interpolation that is faster and achieves state-of-the-art results at high resolutions, making it more practical for real-world applications.

Contribution

The paper presents a novel splatting-based approach for video frame interpolation that is computationally efficient and effective at high resolutions, outperforming existing methods.

Findings

Faster than similar approaches, especially for multi-frame interpolation.

Achieves state-of-the-art results at high resolutions.

Practical for real-world video editing applications.

Abstract

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.