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. The proposed method wins the 1st place at the video interpolation challenge in ICCV 2019: http://www.vision.ee.ethz.ch/aim19/.

Others

Paper, Code & Model, Data-Davis, Data-UCF, Data-GOPRO, Data-Adobe240, Data-QVI960