Motion Inbetweening via Deep $\Delta$-Interpolator. (arXiv:2201.06701v2 [cs.LG] UPDATED)

We show that the task of synthesizing missing middle frames, commonly known
as motion inbetweening in the animation industry, can be solved more accurately
and effectively if a deep learning interpolator operates in the delta mode,
using the spherical linear interpolator as a baseline. We demonstrate our
empirical findings on the publicly available LaFAN1 dataset. We further
generalize this result by showing that the $\Delta$-regime is viable with
respect to the reference of the last known frame (also known as …

arxiv delta