A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis

arXiv:2308.07301v2 Announce Type: replace
Abstract: The synthesis of human motion has traditionally been addressed through task-dependent models that focus on specific challenges, such as predicting future motions or filling in intermediate poses conditioned on known key-poses. In this paper, we present a novel task-independent model called UNIMASK-M, which can effectively address these challenges using a unified architecture. Our model obtains comparable or better performance than the state-of-the-art in each field. Inspired by Vision Transformers (ViTs), our UNIMASK-M model decomposes a …

arxiv autoencoder cs.cv cs.gr cs.ro masked autoencoder synthesis type