Motion-blurred Video Interpolation and Extrapolation

Abrupt motion of camera or objects in a scene result blurry video, and therefore recovering high quality video requires two types enhancements: visual enhancement temporal upsampling. A broad range research attempted to recover clean frames from blurred image sequences temporally upsample by interpolation, yet there are very limited studies handling both problems jointly. In this work, we present novel framework for deblurring, interpolating extrapolating sharp motion-blurred an end-to-end manner. We design our first learning the pixel-level that caused blur given inputs via optical flow estimation then predict multiple warping decoded features with estimated flows. To ensure coherence across predicted address potential ambiguity, propose simple, effective flow-based rule. The effectiveness favorability approach highlighted through extensive qualitative quantitative evaluations on datasets speed videos.