A single Transformer encoder with zero-filled gaps, root-space features, and velocity inputs achieves state-of-the-art motion in-betweening on LaFAN1, showing that data choices can outweigh model complexity.
Listen, denoise, action! audio-driven motion synthesis with diffusion models.ACM Transactions on Graphics (TOG), 42(4):1–20, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SILK: Smooth InterpoLation frameworK for motion in-betweening A Simplified Computational Approach
A single Transformer encoder with zero-filled gaps, root-space features, and velocity inputs achieves state-of-the-art motion in-betweening on LaFAN1, showing that data choices can outweigh model complexity.