SMGDiff generates real-time, user-controllable soccer animations with an autoregressive diffusion model plus a contact guidance module, trained on a new 1.08-million-frame soccer motion dataset.
Motion matching and the road to next-gen ani- mation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SMGDiff: Soccer Motion Generation using diffusion probabilistic models
SMGDiff generates real-time, user-controllable soccer animations with an autoregressive diffusion model plus a contact guidance module, trained on a new 1.08-million-frame soccer motion dataset.