Controllable Tracking-Based Video Frame Interpolation

Even without any user input, our model achieves state-of-the-art results in challenging test cases. By using points tracked over the whole sequence, we can use better motion trajectory interpolation methods, such as cubic splines, to more accurately represent the true motion and achieve significant improvements in results. Our experiments demonstrate that refining tracks and their trajectories through user interactions significantly improves the quality of interpolated frames.