Motion In-Betweening via Deep $\Delta$Δ-Interpolator
Lists
Only you see this
Abstract
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 $\Delta$ -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.
BibTeX
@article{oreshkin2024motion,
author = {Boris N. Oreshkin and Antonios Valkanas and Félix G. Harvey and Louis-Simon Ménard and Florent Bocquelet and Mark J. Coates},
title = {{Motion In-Betweening via Deep $\textbackslash\{\}Delta$Δ-Interpolator}},
journal = {IEEE Trans. Vis. Comput. Graph.},
year = {2024},
doi = {10.1109/tvcg.2023.3309107},
}Loading related content...