Motion Inbetweening via Deep $Δ$-Interpolator
This work addresses motion inbetweening for animation or robotics, but it appears incremental as it builds on existing interpolation methods with a focus on reference frame improvements.
The paper tackles the problem of synthesizing human motion between key frames by introducing a deep learning interpolator that operates in a delta mode, using spherical linear interpolation as a baseline, and achieves state-of-the-art performance on public datasets.
We show that the task of synthesizing human motion conditioned on a set of key frames can be solved more accurately and effectively if a deep learning based interpolator operates in the delta mode using the spherical linear interpolator as a baseline. We empirically demonstrate the strength of our approach on publicly available datasets achieving state-of-the-art performance. We further generalize these results by showing that the $Δ$-regime is viable with respect to the reference of the last known frame (also known as the zero-velocity model). This supports the more general conclusion that operating in the reference frame local to input frames is more accurate and robust than in the global (world) reference frame advocated in previous work. Our code is publicly available at https://github.com/boreshkinai/delta-interpolator.