Quadratic video interpolation

TL;DR

This paper introduces a quadratic video interpolation method that leverages acceleration information to better model complex motions, resulting in more accurate frame predictions compared to traditional linear models.

Contribution

The paper proposes a novel quadratic interpolation approach that captures acceleration, along with a flow reversal layer and flow refinement techniques for improved video frame synthesis.

Findings

Outperforms linear models on various datasets

Effectively models complex, curvilinear motions

Provides more accurate and realistic interpolated frames

Abstract

Video interpolation is an important problem in computer vision, which helps overcome the temporal limitation of camera sensors. Existing video interpolation methods usually assume uniform motion between consecutive frames and use linear models for interpolation, which cannot well approximate the complex motion in the real world. To address these issues, we propose a quadratic video interpolation method which exploits the acceleration information in videos. This method allows prediction with curvilinear trajectory and variable velocity, and generates more accurate interpolation results. For high-quality frame synthesis, we develop a flow reversal layer to estimate flow fields starting from the unknown target frame to the source frame. In addition, we present techniques for flow refinement. Extensive experiments demonstrate that our approach performs favorably against the existing linear models on a wide variety of video datasets.