Spotlight
Quadratic Video Interpolation
Xiangyu Xu · Li Siyao · Wenxiu Sun · Qian Yin · Ming-Hsuan Yang

Thu Dec 12th 04:40 -- 04:45 PM @ West Ballroom C

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.

Author Information

Xiangyu Xu (Carnegie Mellon University)
Li Siyao (SenseTime Research)
Wenxiu Sun (SenseTime Research)
Qian Yin (Beijing Normal University)
Ming-Hsuan Yang (Google / UC Merced)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors